INDEX

Explanations

behavior

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EndContext

-0.57

')):

-0.56

 disparu

-0.53

 TextAppearance

-0.52

)_/¯

-0.52

diğini

-0.52

packageName

-0.50

]}{

-0.49

 ostavi

-0.48

 financières

-0.48

POSITIVE LOGITS

TagMode

0.76

tagHelperRunner

0.64

SourceChecksum

0.60

card

0.55

enterOuterAlt

0.54

ftagPool

0.54

évaluateur

0.52

ssf

0.50

 cards

0.49

GraphicsUnit

0.49

Activations Density 0.084%