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

èĢ³

-0.30

Chance

-0.27

gain

-0.27

ä¹ŁåºĶè¯¥

-0.25

dash

-0.25

ê²Ĳ

-0.24

ä¸įå®ľ

-0.24

æ±Ĺ

-0.24

afari

-0.23

 Mutation

-0.23

POSITIVE LOGITS

cri

0.30

å¤§éĻĨ

0.27

ç¾¯

0.27

 adel

0.26

 melted

0.25

adoo

0.25

 Moved

0.25

æĸ¹åľĨ

0.25

thy

0.24

 lamb

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.