INDEX

Explanations

harmful or offensive content

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pause

1.41

ancar

1.37

pause

1.35

噔

1.33

antom

1.30

blast

1.30

icias

1.29

 timer

1.28

 cellpadding

1.28

äte

1.26

POSITIVE LOGITS

 เท่า

1.80

 određ

1.63

 vodu

1.59

的对象

1.52

 fisik

1.48

 részt

1.48

'{}

1.47

ciplinary

1.42

usw

1.41

dll

1.41

Activations Density 0.039%