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

izaci

0.42

 Jacoby

0.41

 innings

0.40

 Freeway

0.39

nings

0.38

 pelajaran

0.38

"]).

0.37

返し

0.37

ებისთვის

0.37

 ಒಳ್ಳೆಯ

0.37

POSITIVE LOGITS

safe

0.43

 safe

0.41

 assuring

0.41

on

0.41

Safe

0.40

 ster

0.39

 Safe

0.38

 assured

0.38

uje

0.38

 assurance

0.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.