INDEX

Explanations

code/equations

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

mando

-0.28

å±ŀ

-0.27

ej

-0.27

 Ally

-0.26

amp

-0.26

 objectId

-0.26

 echoed

-0.25

ä¸ĢäºĮ

-0.25

man

-0.25

pty

-0.24

POSITIVE LOGITS

æŃ¥ä¼Ĳ

0.28

vents

0.27

æĮĤéĴ©

0.26

é³į

0.26

lement

0.26

 Prostit

0.26

ois

0.24

bsites

0.24

è´¿èµĤ

0.23

 festivals

0.23

Activations Density 0.101%