INDEX

Explanations

at

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

Personensuche

-0.70

#+#

-0.65

Cartney

-0.59

 nigra

-0.50

 lenker

-0.47

PointerException

-0.47

rlpool

-0.47

 rospy

-0.46

AnimationsModule

-0.45

NullException

-0.45

POSITIVE LOGITS

 Scale

0.63

 scale

0.63

Scale

0.56

titud

0.53

scale

0.52

 skala

0.52

SCALE

0.51

 SCALE

0.51

Times

0.51

 Times

0.51

Activations Density 0.007%