INDEX

Explanations

Def

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

æľªæĪĲ

-0.29

ÑĥÑĢÑģ

-0.28

ä¹ĭå¿ĥ

-0.27

 persist

-0.26

unda

-0.26

á»³

-0.25

è¸Ĭ

-0.25

-par

-0.25

 persists

-0.24

æ»ĳ

-0.24

POSITIVE LOGITS

 Suff

0.30

äºĴåĬ©

0.29

assing

0.28

 enough

0.27

suf

0.27

assen

0.26

å¤Ł

0.25

çłĶç©¶æīĢ

0.25

åħµ

0.25

åħħè¶³çļĦ

0.24

Activations Density 0.885%