INDEX

Explanations

also

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

AndEndTag

-0.79

 genoux

-0.61

 vuotta

-0.59

johtaja

-0.57

Diwedd

-0.56

PerformLayout

-0.56

didSet

-0.54

 <>",

-0.54

 AttributeSet

-0.54

UnusedPrivate

-0.54

POSITIVE LOGITS

 true

0.76

 possible

0.65

 knows

0.54

to

0.54

true

0.54

 vrai

0.54

 seen

0.52

 takes

0.52

 operates

0.52

)"),

0.50

Activations Density 0.066%