INDEX

Explanations

words related to contradiction and being not in agreement

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

toHaveBeenCalled

-0.80

存于互联网档案馆

-0.73

 Shared

-0.63

avyzd

-0.63

Shared

-0.62

uxxxx

-0.60

 meille

-0.59

govia

-0.59

følgelig

-0.59

Демографія

-0.58

POSITIVE LOGITS

 contradictory

0.60

 contradictions

0.57

 tardi

0.53

 contradiction

0.50

 OpenSSL

0.50

 Daryl

0.48

stående

0.48

ULER

0.48

absolutely

0.47

 hardly

0.47

Activations Density 0.022%