INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 Completion

0.38

Monument

0.38

 thumbs

0.38

Garden

0.37

嘘

0.37

CLAIM

0.37

 пей

0.37

có

0.36

marine

0.35

 Monument

0.35

POSITIVE LOGITS

\<

0.40

 bowled

0.39

 seiner

0.37

 grabbed

0.37

 Ashley

0.37

лып

0.37

getP

0.37

 uiteindelijk

0.36

তিপ

0.35

 scegli

0.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.