INDEX

Explanations

scientific texts

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ChildScrollView

-0.80

 незавершена

-0.79

featureID

-0.78

Brainz

-0.77

 Савезне

-0.77

 Normdatei

-0.75

tagHelperRunner

-0.73

 referenties

-0.71

 Picchu

-0.68

buttonBar

-0.68

POSITIVE LOGITS

ras

0.51

cond

0.51

cs

0.50

kom

0.49

افت

0.48

cados

0.47

 Го

0.47

cado

0.46

Clar

0.46

 kích

0.46

Activations Density 0.001%