INDEX

Explanations

val

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

val

-0.95

res

-0.81

 Majefty

-0.73

 BoxDecoration

-0.72

azy

-0.69

tably

-0.66

 sees

-0.65

 Sees

-0.63

Res

-0.62

hip

-0.62

POSITIVE LOGITS

er

0.69

ی

0.63

ing

0.61

erick

0.59

 lät

0.55

ه

0.52

inga

0.49

encer

0.48

erende

0.48

eria

0.48

Activations Density 0.271%