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

cents

-0.28

/Runtime

-0.27

quarters

-0.27

-center

-0.27

ä¸Ńå¿ĥ

-0.26

 centers

-0.26

odore

-0.26

iaux

-0.25

papers

-0.24

illator

-0.24

POSITIVE LOGITS

hani

0.31

ä¸Ģæ¬¾

0.27

åĽ½æ°ĳ

0.27

å··

0.25

åĺĮ

0.24

ë³¸

0.24

è¡Ĺä¸Ĭ

0.24

street

0.23

ä¸ĭäºĨ

0.23

 Ð½Ð°Ð¿ÑĢÐ°Ð²Ð»ÐµÐ½

0.23

Activations Density 0.926%

No Known Activations

This feature has no known activations.