INDEX

Explanations

code or question marker

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

 unicórnio

-1.28

 pulseras

-1.27

 pneus

-1.22

 tênis

-1.20

ότητα

-1.19

'];

-1.18

 потім

-1.16

蟊

-1.16

 frança

-1.16

*/,

-1.16

POSITIVE LOGITS

<bos>

1.35

1.15

1.01

据说

0.97

アプリケーション

0.97

เตอร์

0.97

からず

0.96

 entorno

0.94

それに

0.93

关心

0.92

Activations Density 0.000%