INDEX

Explanations

the word "like" and words close to it.

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

RegistryLite

-0.52

Parcelize

-0.47

 lomb

-0.46

 ***!

-0.46

 infil

-0.44

ұ

-0.43

,_

-0.43

Batis

-0.43

TagMode

-0.43

!(:

-0.42

POSITIVE LOGITS

Efq

0.72

 буквально

0.70

 literally

0.68

 Chrift

0.65

 متعلقه

0.65

awtextra

0.63

 Literally

0.63

 Jefus

0.63

 ſeveral

0.63

 theſe

0.62

Activations Density 0.015%