Role Manager

Role Manager allows you to limit access to individual GPT AI Power features based on user roles assigned on your website. To access the Role Manager, hover over GPT AI Power’s menu entry in the WordPress menu, and click Role Manager in the submenu that appears. Upon reaching the Role Manager, you’ll see a range […]

Selecting GPT Model

GPT AI Power exclusively supports OpenAI GPT-3, GPT-3.5 and GPT-4 models. Please be aware that GPT-4 is currently in limited beta, which means that access to the GPT-4 API from OpenAI is available only through a waiting list and is not open to everyone yet. You can sign up for the waiting list at here. […]

OpenAI Error List

This post provides an overview of common error codes and their corresponding solutions. Each error code is explained in detail in its own dedicated section. 401 – Invalid Authentication. Cause: Invalid Authentication Solution: Ensure the correct API key and requesting organization are being used. 401 – Incorrect API key provided Cause: The requesting API key […]

Presence Penalty

Presence Penalty is between -2.0 and 2.0 and it impacts how the model penalizes new tokens based on whether they have appeared in the text so far. Positive values will increase the likelihood of the model talking about new topics by penalizing new tokens that have already been used. The presence penalty is a one-time, […]

Frequency Penalty

Frequency Penalty is between -2.0 and 2.0 and it impacts how the model penalizes new tokens based on their existing frequency in the text. Positive values will decrease the likelihood of the model repeating the same line verbatim by penalizing new tokens that have already been used frequently. The presence penalty is a one-time, additive […]

Best Of

Best Of generates multiple candidate completions on the OpenAI side and returns the “best” ones based on the highest log probability per token. Please be aware that using this parameter may quickly consume your token quota, so it is important to use it carefully and to adjust the “max_tokens” setting appropriately. You can adjust this […]


An alternative to sampling with temperature is called nucleus sampling, in which the model only takes into account the tokens with the highest probability mass (as determined by the top_p parameter). For example, a value of 0.1 means that only the tokens with the top 10% probability mass are considered. OpenAI generally recommends to use […]

GPT Max Tokens

OpenAI language model processes text by dividing it into tokens, which can be individual words or groups of characters. For example, the word “fantastic” would be split into the tokens “fan”, “tas”, and “tic”, while a shorter word like “gold” would be considered a single token. Many tokens start with a space, such as ” […]

GPT Temperature Settings

Temperature is an important setting in GPT that has a significant impact on the output of the system. It controls the amount of randomness in the output, and can be adjusted to achieve different results. At lower temperatures, GPT will tend to choose words with a higher probability of occurrence, which can be useful when […]