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

åĴĮå¹³

-0.28

crement

-0.28

åħ±åĲĮ

-0.26

eters

-0.25

áº©n

-0.25

onical

-0.24

ç«ŀäºīä¼ĺåĬ¿

-0.24

unk

-0.23

åįķåįķ

-0.23

 PROF

-0.23

POSITIVE LOGITS

oire

0.29

bole

0.28

ä¿®èº«

0.27

ikon

0.26

esso

0.26

åĮ¯

0.26

phere

0.25

?page

0.24

æīįä¼ļ

0.24

Ã¶rt

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.