INDEX

Explanations

descriptive adjectives for entities

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

to

-1.46

-1.38

 their

-1.38

it

-1.30

any

-1.28

 thier

-1.23

-1.20

ഛ

-1.17

or

-1.15

옳

-1.13

POSITIVE LOGITS

 warszawa

1.51

 stary

1.34

1.30

řízení

1.29

蛭

1.27

¹.

1.26

zić

1.23

<bos>

1.23

 karier

1.22

uch

1.21

Activations Density 0.141%