INDEX

Explanations

identifying people and their actions

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

 females

0.62

 themselves

0.60

 іх

0.54

Female

0.53

 female

0.52

mselves

0.51

their

0.50

 Female

0.49

 loro

0.49

 Females

0.48

POSITIVE LOGITS

 named

0.66

 bernama

0.60

 llamado

0.59

 اسمه

0.57

atee

0.54

ዬ

0.52

 nommé

0.52

 Named

0.52

Named

0.50

 wearing

0.49

Activations Density 0.030%