INDEX

Explanations

find or see something

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

"));

-1.42

babies

-1.38

 does

-1.37

</h2>

-1.36

-1.34

 allow

-1.31

-1.30

 those

-1.29

 家居

-1.28

 will

-1.27

POSITIVE LOGITS

 dari

1.70

 terke

1.61

 olvido

1.61

 informé

1.60

 menyadari

1.54

 gorro

1.52

ことがある

1.50

ﾃ

1.49

 botanique

1.48

 trouverez

1.48

Activations Density 0.024%