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

 harm

-0.29

æľīæĽ´å¥½çļĦ

-0.28

olas

-0.27

è·Łä»ĸ

-0.27

 ìĦ

-0.26

oko

-0.26

 right

-0.26

ocket

-0.25

luck

-0.25

 diamonds

-0.25

POSITIVE LOGITS

 deflate

0.28

 handle

0.27

-handle

0.27

.gnu

0.26

lish

0.26

Heb

0.26

 Units

0.25

 units

0.25

bum

0.24

éĥģ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.