INDEX

Explanations

code block punctuation

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

 also

-1.61

 Ако

-1.40

🎦

-1.38

 вашего

-1.35

 tambien

-1.29

Also

-1.28

 любого

-1.27

 también

-1.24

InitStructure

-1.23

cnico

-1.22

POSITIVE LOGITS

näm

1.36

閲覧

1.29

it

1.27

 '/':

1.23

 która

1.23

возь

1.22

 quieran

1.18

 メニュー

1.18

łada

1.17

新潟

1.16

Activations Density 0.087%