INDEX

Explanations

Cord

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ukone

-0.60

InitVars

-0.56

roots

-0.56

ruary

-0.56

kmäler

-0.54

دانشنامهٔ

-0.53

mush

-0.52

ctober

-0.52

nocache

-0.51

ateness

-0.50

POSITIVE LOGITS

 strung

0.48

 Deformation

0.48

AddHtmlAttribute

0.48

InputBorder

0.48

 Slaughter

0.47

ConstraintMaker

0.47

 Stamps

0.47

 strangled

0.46

 Alvar

0.45

OuterClass

0.45

Activations Density 0.007%