INDEX

Explanations

numbers and punctuation

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

 other

-1.59

其它

-1.39

 innych

-1.39

其他人

-1.32

อื่น

-1.31

 anderer

-1.31

其他

-1.30

Väl

-1.30

Другие

-1.28

웬

-1.27

POSITIVE LOGITS

–

1.47

 cualquier

1.36

kowa

1.35

 nyní

1.34

𝕂

1.31

襌

1.27

 qualquer

1.24

 своим

1.23

 безопасности

1.23

 класси

1.22

Activations Density 0.001%