INDEX

Explanations

language descriptions

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

athletes

1.23

igment

1.20

ván

1.19

መል

1.19

んでいた

1.18

chol

1.17

imid

1.16

 নির্যাতন

1.13

 atletas

1.10

 luyện

1.10

POSITIVE LOGITS

1.34

하고

1.18

와

1.17

،

1.14

и

1.10

と

1.07

∪

1.04

 текст

1.03

و

1.03

，

1.02

Activations Density 0.000%