INDEX

Explanations

special characters 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

為に

-1.52

 izman

-1.29

 arī

-1.27

 comprometido

-1.24

ļ

-1.23

 constantemente

-1.22

levis

-1.21

 īpa

-1.17

 atento

-1.17

 decidido

-1.17

POSITIVE LOGITS

<bos>

1.55

曲は

1.27

つまり

1.15

とはいえ

1.13

wać

1.12

ilarang

1.09

gemeester

1.07

特長

1.07

__':

1.06

これに

1.05

Activations Density 0.006%