INDEX

Explanations

scores separated by hyphens

numbers and punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

Constraints

0.44

errorMessage

0.43

뀨

0.43

encodeWith

0.42

𝗎

0.42

કિસ્

0.41

 outcomes

0.41

outcome

0.40

Outcome

0.40

тером

0.40

POSITIVE LOGITS

 will

0.38

":

0.37

 Rape

0.36

',

0.36

 terça

0.36

 Benito

0.36

 Dhawan

0.36

وجه

0.36

 Tsuen

0.36

月

0.36

Activations Density 0.001%