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

isode

-0.27

anela

-0.26

renched

-0.26

ohl

-0.25

 diag

-0.25

ä½ľèĢħæľ¬äºº

-0.25

 Mell

-0.25

ç»ıéĶĢ

-0.24

anvas

-0.24

erness

-0.24

POSITIVE LOGITS

å½

0.27

 crow

0.27

-brand

0.26

æħ£

0.25

 NotFoundException

0.25

tank

0.25

åĪĨå¼Ģ

0.25

($__

0.25

çĤ¹å¤´

0.24

uju

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.