INDEX

Explanations

mentions of a specific individual's name

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.66

msgTypes

-0.61

 exaggeration

-0.56

 Bobby

-0.55

 exaggerate

-0.54

 Maho

-0.53

OptionsMenu

-0.52

acetate

-0.52

 exaggerated

-0.51

 للمعارف

-0.51

POSITIVE LOGITS

Roy

1.16

Roy

0.95

cemia

0.86

 arrhyth

0.80

 categorical

0.80

ROY

0.79

glycemia

0.75

categorical

0.73

ftagPool

0.67

RunWith

0.66

Activations Density 0.003%