INDEX

Explanations

No Explanations Found

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

pton

-0.26

edd

-0.26

æ´²

-0.25

éĿĻ

-0.25

eya

-0.25

uno

-0.25

elts

-0.24

pter

-0.24

Alt

-0.24

aturing

-0.24

POSITIVE LOGITS

å¥½äºĭ

0.28

çĶ³

0.27

 Charg

0.26

Loaded

0.26

 inher

0.25

iaz

0.25

/use

0.25

çĶ³æĬ¥

0.24

èļ¤

0.24

RAND

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.