INDEX

Explanations

No Explanations Found

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

 невероят

0.51

 пространства

0.51

હ

0.50

 कठिन

0.49

ጥ

0.49

",[],"

0.48

 onPressed

0.48

 явно

0.48

 असुर

0.47

ム

0.47

POSITIVE LOGITS

 average

0.46

 native

0.45

—

0.45

own

0.42

archive

0.42

 finally

0.42

 transcripts

0.41

self

0.40

 Native

0.40

 each

0.39

Activations Density 0.009%

No Known Activations