INDEX

Explanations

Geographic locations and historical figures

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

rigger

-0.84

 solitaire

-0.81

elni

-0.78

 VICTORIA

-0.77

aix

-0.77

dě

-0.75

 juger

-0.72

Ibn

-0.72

 ALUMIN

-0.72

 assurer

-0.72

POSITIVE LOGITS

 Brody

0.96

Vol

0.91

 Poles

0.88

 Polish

0.84

 Galicia

0.83

 Jews

0.82

Vol

0.77

Б

0.77

 Lublin

0.77

 نش

0.74

Activations Density 0.034%