INDEX

Explanations

Nazi and Soviet entities

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

Adolf

-1.16

Nazi

-1.09

 キーホルダー

-1.00

Transk

-0.97

 かわいい

-0.95

鳧

-0.94

 nazi

-0.93

 potret

-0.91

Privat

-0.91

Hitler

-0.90

POSITIVE LOGITS

era

1.42

 Germany

1.15

 China

1.13

 Australia

1.08

 America

1.05

 Brazil

1.05

 Scotland

1.05

 Florida

1.04

 officials

1.02

 Ireland

1.02

Activations Density 0.023%