INDEX

Explanations

proper nouns and specific terms

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

蛩

-2.66

-2.41

chappen

-2.27

σει

-2.23

しました

-2.22

 продукт

-2.19

此时

-2.17

</h1>

-2.16

⢌

-2.16

ly

-2.14

POSITIVE LOGITS

寕

3.78

⸫

2.81

 Hinblick

2.81

 keineswegs

2.55

 predetermined

2.50

</em>

2.47

 nemico

2.44

镦

2.42

 Einzelnen

2.41

௜

2.39

Activations Density 0.100%