INDEX

Explanations

initials and affiliations

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

 while

-1.63

 those

-1.41

any

-1.41

it

-1.38

 because

-1.29

on

-1.27

 that

-1.20

を行います

-1.17

ための

-1.17

を行いました

-1.16

POSITIVE LOGITS

 作り方

1.47

bbons

1.25

Bjs

1.24

และ

1.22

两个

1.20

توضیحات

1.20

 tristes

1.20

 dwóch

1.17

dekor

1.17

tikai

1.16

Activations Density 0.014%