INDEX

Explanations

promoting prejudice and discrimination

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

 femminile

0.55

 feminine

0.54

女性

0.50

 жі

0.49

female

0.48

Female

0.47

 feminina

0.47

femin

0.47

 fémin

0.46

ktop

0.46

POSITIVE LOGITS

 prejudice

1.62

 hatred

1.52

 hate

1.41

 bigotry

1.41

 prejudices

1.40

 prejudiced

1.38

 discrimination

1.35

 Prejudice

1.35

 racism

1.25

 hateful

1.25

Activations Density 0.055%