INDEX

Explanations

code, paths, and names

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

abol

-0.28

ago

-0.26

èº«æĿĲ

-0.25

 cast

-0.25

ç¬®

-0.25

 fours

-0.24

Ĩ

-0.23

 mapped

-0.23

ä¸ĢåĲ¬

-0.23

åĽĽç§į

-0.23

POSITIVE LOGITS

lix

0.29

 giÃ³

0.27

Î®

0.26

ÑĢÐ°Ðº

0.25

ÑĪÐºÐ°

0.25

èĢģå¤´

0.25

_digest

0.24

[arg

0.24

ELY

0.24

æ°ħ

0.23

Activations Density 0.004%