INDEX

Explanations

subject

language regarding rules and conditions

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

 myſelf

-0.91

contentLoaded

-0.82

 itſelf

-0.80

 pleaſure

-0.75

 ་་

-0.73

PLW

-0.72

 متعلقه

-0.71

 Monfieur

-0.69

Efq

-0.69

 ―――――

-0.68

POSITIVE LOGITS

ביוגרפיה

0.50

to

0.49

MemoryWarning

0.48

וויק

0.48

zcze

0.47

 RENE

0.44

randall

0.41

$_['

0.41

 szóci

0.40

 годов

0.40

Activations Density 1.307%