INDEX

Explanations

hesitation, interjections, and symbols

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

*{

0.41

 truly

0.40

too

0.40

Sau

0.38

!`

0.37

र्ट

0.36

ंझ

0.36

 लायक

0.36

ាយ

0.36

лишком

0.36

POSITIVE LOGITS

uh

0.56

Uh

0.52

um

0.47

 raczej

0.46

呃

0.45

………..

0.45

Uh

0.44

 congrats

0.44

………

0.42

……….

0.42

Activations Density 0.034%