INDEX

Explanations

hang

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

 hang

-0.77

Gambas

-0.71

SourceChecksum

-0.70

 useStyles

-0.66

 ostavi

-0.65

 hung

-0.64

Hang

-0.63

 للاسماء

-0.62

 Hang

-0.60

 hangs

-0.59

POSITIVE LOGITS

BeginContext

0.51

?[

0.46

 uproar

0.45

 dises

0.44

 livid

0.44

<?

0.43

EDEFAULT

0.43

กัน

0.43

 hypocrite

0.43

azu

0.42

Activations Density 0.009%