INDEX

Explanations

version numbers, identifiers

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

三十

-1.19

 these

-1.16

his

-1.16

政治

-1.16

for

-1.14

二十

-1.12

of

-1.10

 katholischen

-1.09

ｃ

-1.06

福祉

-1.05

POSITIVE LOGITS

関連リンク

1.33

すみません

1.31

ごめん

1.26

解决方案

1.23

órias

1.19

 Choisissez

1.17

のお話

1.17

äuser

1.16

お前

1.16

おそ

1.16

Activations Density 0.037%