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

æİĴ

-0.28

å¡Ķ

-0.26

awei

-0.25

ponge

-0.24

roles

-0.24

heid

-0.24

è®¸

-0.24

oka

-0.24

 lille

-0.24

erk

-0.24

POSITIVE LOGITS

zar

0.28

 designs

0.27

ä¸ªé¡¹çĽ®

0.26

 harmless

0.24

 divider

0.24

é¥±

0.24

 Entry

0.23

à¹ģà¸ļ

0.23

 entry

0.23

_Entry

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.