Please enter your API key in the Settings page.
Go to Settings
Summarize
Submit
Save
Clear
Length
100
Temp
0.5
Top P
1
Freq
0.2
Presence
0
Controls the approximate length of model completions, in words.
Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive.
Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.
How much to penalize new tokens based on their existing frequency in the text so far. Decreases the model's likelihood to repeat the same line verbatim.
How much to penalize new tokens based on whether they appear in the text so far. Increases the model's likelihood to talk about new topics.
Start sequence
Restart sequence
Stop sequence
Library
History Saved
No history
Nothing saved
Community
Coming soon
Settings
API KEY
  • Your API key does not leave your browser. Find your key here.
  • No key? Join the circus.
  • OUTPUT FILTERING
  • Flag toxicity
  • Show probabilities
  • MODEL
  • ada
  • babbage
  • curie
  • davinci
  • ABOUT
    OpenAI Circus is built by Sundeep Gottipati and Seungho Yang. We are not affiliated with OpenAI. We are just excited by the possibilities.

    Email us at team [at] memos.org
    Circus Community Library Settings