INDEX

Explanations

capitalized last names, particularly authors cited within a document

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

No Comments

Negative Logits

FunctionFlags

-0.77

ArgumentParser

-0.67

 CommandType

-0.65

cticut

-0.63

 MainAxisSize

-0.63

ienki

-0.60

owulf

-0.60

Fas

-0.59

OGND

-0.59

bim

-0.59

POSITIVE LOGITS

 Donny

0.82

 Stich

0.78

 Trey

0.77

 Blau

0.77

IsContent

0.77

 Leeuwen

0.75

 Ishi

0.73

Nak

0.73

 Samar

0.73

 optic

0.72

Activations Density 0.396%