INDEX

Explanations

derogatory sexualized female terms

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

盆

0.40

 ассорти

0.37

Laz

0.36

Saf

0.36

ಗಾರ

0.36

roben

0.36

 sensory

0.35

ঢাকার

0.35

絢

0.35

 Bliss

0.35

POSITIVE LOGITS

 bitch

2.09

 bitches

1.77

 whore

1.55

 slut

1.47

slut

1.20

 promiscu

1.18

 prostitute

1.16

婊

1.16

 prostit

1.09

 prostitutes

1.01

Activations Density 0.034%