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

OMPI

-0.28

cie

-0.28

cio

-0.28

liches

-0.26

Enumerable

-0.25

ä¸ĢåĪ»

-0.25

èİ³

-0.25

emodel

-0.25

é¹¦

-0.25

asion

-0.25

POSITIVE LOGITS

 sonst

0.30

Bad

0.29

 Hard

0.28

Loc

0.27

 ReturnValue

0.27

 Return

0.27

 Supply

0.27

åĨį

0.26

Ret

0.26

Activations Density 0.011%

No Known Activations

This feature has no known activations.