INDEX

Explanations

foreign language fragments

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

हम

-1.37

ども

-1.34

–

-1.30

 professores

-1.24

จาก

-1.24

商品の

-1.21

<>());

-1.16

 Après

-1.16

初め

-1.16

Έ

-1.14

POSITIVE LOGITS

 when

1.37

 beinahe

1.33

ñ

1.15

 while

1.13

 conductas

1.09

 tevens

1.05

his

1.05

 außerdem

1.05

1.04

 cuando

1.03

Activations Density 0.011%