INDEX

Explanations

stereotypes and common perceptions

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

NMR

0.43

 ಉತ್ತಮ

0.39

liquer

0.37

يكم

0.37

NMR

0.36

 ентите

0.36

沚

0.36

 مرا

0.36

MRT

0.35

IO

0.35

POSITIVE LOGITS

 stereotype

1.68

 stereotypes

1.59

 stereotyp

1.55

 stereotypical

1.55

 стере

1.23

 popularly

1.16

 Stere

1.15

stere

1.13

 perceptions

1.13

 estere

1.13

Activations Density 0.068%