INDEX

Explanations

words or phrases related to law enforcement, specifically police officers, but sometimes detects concepts opposite police, like race or racism

cop

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

Negative Logits

cop

-0.77

cop

-0.65

Cop

-0.65

Cop

-0.57

 gran

-0.56

gran

-0.54

sf

-0.54

ono

-0.53

cope

-0.51

sf

-0.48

POSITIVE LOGITS

uxxxx

0.90

 kasarigan

0.89

 nakalista

0.83

Personendaten

0.82

RenderAtEndOf

0.81

adpleegd

0.81

 مرئيه

0.79

 متعلقه

0.78

ForValue

0.78

NewUrlParser

0.77

Activations Density 6.978%