INDEX

Explanations

specific descriptive nouns

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

 last

-1.09

вість

-1.08

 other

-1.05

 conceptually

-1.02

 दौर

-1.00

 bosco

-0.98

devtool

-0.98

Sw

-0.98

 matang

-0.96

 endearing

-0.96

POSITIVE LOGITS

 EXCELL

1.09

 וג

1.05

 vendeur

1.02

 rám

0.97

分からない

0.96

 sám

0.94

and

0.94

 EASY

0.92

 seguridad

0.92

 incendie

0.91

Activations Density 0.120%