INDEX

Explanations

not speaking a word

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

oths

0.41

 slightly

0.40

誠

0.39

 iteratively

0.39

 terminate

0.37

뉘

0.37

反复

0.37

 약간

0.37

 repeating

0.36

 Sprinkle

0.36

POSITIVE LOGITS

 comment

0.56

comment

0.54

 comentario

0.54

coherent

0.52

speech

0.51

 intelligible

0.50

 coment

0.50

 koment

0.50

 speech

0.49

 coherent

0.49

Activations Density 0.012%