INDEX

Explanations

describing degree of feeling

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

 stupid

0.56

 stupidity

0.51

 filth

0.49

 outrageous

0.49

 falsch

0.49

 shitty

0.46

 पागल

0.43

 Stupid

0.42

错了

0.41

 гря

0.41

POSITIVE LOGITS

 somewhat

1.66

 Somewhat

1.31

 quite

1.30

 rather

1.28

 bastante

1.23

 довольно

1.23

 agak

1.22

有點

1.16

 piuttosto

1.15

좀

1.13

Activations Density 0.073%