INDEX

Explanations

conflict and political groups

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

 itſelf

-1.05

 Monfieur

-1.05

ſelf

-1.00

 himſelf

-0.99

 myſelf

-0.99

 themſelves

-0.94

 Theſe

-0.94

 uſe

-0.91

 ſeveral

-0.91

 Houſe

-0.90

POSITIVE LOGITS

de

0.55

 world

0.52

0.50

Ro

0.50

Eloquent

0.50

ha

0.49

Se

0.49

“

0.48

Activations Density 0.068%