INDEX

Explanations

physical impact, strikes, and assault

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

getZoom

0.40

霝

0.40

驪

0.39

 pronunci

0.38

 narrowband

0.38

transparent

0.38

 వ్యవ

0.38

polarity

0.37

址

0.37

 фраг

0.37

POSITIVE LOGITS

 punches

1.71

 punching

1.68

 punch

1.51

 punched

1.51

Punch

1.35

 slapping

1.33

punch

1.32

殴

1.30

 Punch

1.29

 fists

1.23

Activations Density 0.073%