INDEX

Explanations

words related to calendar events, medical terms, years, and potential criminal activity

seemingly random strings of characters and numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

...

-0.48

 Courtney

-0.45

…

-0.44

kenen

-0.43

nga

-0.43

drawSprites

-0.43

Dichloroethane

-0.42

vičius

-0.42

 performance

-0.42

igte

-0.42

POSITIVE LOGITS

IsContent

1.02

numerusform

0.75

TagMode

0.66

enumii

0.66

 fédé

0.65

脚注の使い方

0.65

CloseOperation

0.63

+#+#

0.63

BeginContext

0.63

Gön

0.62

Activations Density 1.265%