INDEX

Explanations

England

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 England

-0.79

 English

-0.78

 english

-0.69

Eng

-0.68

English

-0.65

uk

-0.63

 surla

-0.59

ENGLISH

-0.57

 ENGLISH

-0.57

England

-0.55

POSITIVE LOGITS

 Theſe

1.02

 Majefty

0.97

 Houſe

0.94

 houſe

0.93

 Anſ

0.93

 ſeveral

0.87

 ſche

0.87

 Reſ

0.86

 Jefus

0.85

 myſelf

0.84

Activations Density 0.725%