INDEX

Explanations

references to a specific federal agency involved in immigration enforcement

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

IMO

-0.76

Према

-0.75

 purpoſe

-0.74

ſelves

-0.73

 itſelf

-0.73

 ويكيميديا

-0.70

 faſt

-0.70

 poffible

-0.70

 ſche

-0.69

 Aéroport

-0.69

POSITIVE LOGITS

bia

3.05

BIA

1.69

bial

1.41

bias

1.30

bia

1.29

Bia

1.27

Bia

1.12

BIAS

0.84

ibia

0.84

Bias

0.77

Activations Density 0.001%