INDEX

Explanations

professions followed by descriptive clauses

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Coming

0.52

 이름

0.52

 이름을

0.51

 coming

0.49

Coming

0.48

coming

0.45

 names

0.44

 getName

0.43

웨

0.43

 name

0.42

POSITIVE LOGITS

訝

0.45

 sinking

0.40

 unsatisfied

0.39

 depressed

0.39

Kyr

0.37

 terrified

0.36

发生

0.35

 प्रतिबंधित

0.34

 frightened

0.34

άσ

0.33

Activations Density 0.013%