INDEX

Explanations

newcomers and immigrants

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

〟

-0.90

yng

-0.88

tyn

-0.87

banner

-0.85

 adal

-0.84

 XXVIII

-0.84

Ģ

-0.83

 WOMAN

-0.82

 koel

-0.82

је

-0.82

POSITIVE LOGITS

 immigrants

1.79

 immigration

1.69

 language

1.65

immig

1.55

 newcomer

1.54

 assimilation

1.52

 immigrant

1.49

 newcomers

1.48

 integration

1.41

 Immigration

1.40

Activations Density 0.044%