INDEX

Explanations

XML attributes and code tags

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

any

-1.35

 might

-1.30

 while

-1.28

new

-1.26

 that

-1.25

 could

-1.24

 first

-1.15

 trying

-1.11

喽

-1.07

 just

-1.06

POSITIVE LOGITS

 faſt

1.57

 花纹

1.52

 ſever

1.47

ಱ

1.45

оо

1.45

 唯美

1.45

 miſ

1.44

 époux

1.43

EVERY

1.39

два

1.35

Activations Density 0.049%