INDEX

Explanations

mathematical expressions and code snippets

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

<bos>

-1.60

了很多

-1.43

人也

-1.34

 molte

-1.33

 gênero

-1.30

有不少

-1.28

-1.27

%;

-1.27

 origins

-1.27

ouncements

-1.26

POSITIVE LOGITS

or

1.91

as

1.59

in

1.42

on

1.34

 explicar

1.32

อีก

1.29

خابات

1.26

⛈

1.25

 geweldig

1.25

 nacidos

1.24

Activations Density 0.139%