INDEX

Explanations

help, about, and usage information

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

 sinds

-1.45

푆

-1.38

 that

-1.35

𝙺

-1.19

土豆

-1.17

コミック

-1.13

ienze

-1.13

皆さま

-1.13

 фаса

-1.13

 které

-1.10

POSITIVE LOGITS

 about

1.59

“

1.38

 verbreitet

1.33

’”

1.32

<em>

1.32

 “(

1.29

 “.

1.27

…”

1.24

↵

1.23

uszcz

1.21

Activations Density 0.065%