Temperature is a sampling hyperparameter that controls randomness in token selection; higher values increase diversity, lower values favor likely tokens.
AI Glossary
Temperature
Coverage in development
Temperature is a sampling hyperparameter that controls randomness in token selection; higher values increase diversity, lower values favor likely tokens.
Definition
Plain English explanation
Turn it up for more creative variety; turn it down for more predictable answers.
Related glossary terms
Last reviewed
Sources
- NIST AI Risk Management Framework — risk vocabulary context for AI systems
- Brel Digital company and technology profiles — applied usage evidence where tagged
Correction request
If a technology assignment or hub description is inaccurate, submit a correction via the Corrections Policy.
All technologies → · AI Models → · APIs & SDKs → · Integrations → · Compliance → · Browse all companies → · Explore industries → · Compare →