INDEX

Explanations

done without permission or warning

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

\}$,

-1.46

츨

-1.42

'},

-1.36

 Inver

-1.36

+}$

-1.35

titial

-1.34

OOOOO

-1.34

﹍﹍

-1.30



-1.30

biť

-1.29

POSITIVE LOGITS

The

1.57

our

1.52

two

1.41

it

1.37

Policies

1.34

 พ่อ

1.23

 going

1.22

or

1.22

 благодаря

1.22

ly

1.20

Activations Density 0.048%