INDEX

Explanations

when a person recognizes their own identity or presence

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.83

 autorytatywna

-0.79

 itself

-0.78

 OFDb

-0.76

 Administrativna

-0.66

Bronnen

-0.65

Bakgrunnsstoff

-0.65

กัน

-0.64

BrowserModule

-0.63

InitVars

-0.63

POSITIVE LOGITS

 herself

2.28

herself

1.68

 ihrem

0.76

 cantik

0.63

 koja

0.63

 née

0.59

 рассказала

0.59

 сказала

0.57

 ihren

0.54

 spokeswoman

0.54

Activations Density 0.002%