AI glossary · Prompts and settings
Top-p
Top-p is a setting that limits an AI’s word choices to its most likely options, such as those making up 90% of the probability. Lower values are more focused.
Also called nucleus sampling
In more detail
With top-p set to 0.1, the model only considers the few tokens that make up the top 10% of probability. At 1, it considers everything.
It is an alternative to temperature for controlling variety. Providers usually suggest adjusting one or the other, not both.
Related terms
TemperatureTemperature is a setting that controls how random or creative an AI’s output is. Low values give focused, predictable answers; high values, more varied ones.TokenA token is a small chunk of text, often a word or part of a word, that a language model reads and writes. Usage limits and prices are counted in tokens.Frequency penaltyFrequency penalty is a setting that discourages an AI from repeating the same words, with a stronger effect the more often a word has already appeared.
Browse related tools
AI tools listed on BroUseAI in these categories.
