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

onis

-0.29

 diÃ¡

-0.28

 phon

-0.25

 batteries

-0.24

Ã¢m

-0.24

tea

-0.24

 gran

-0.24

 german

-0.23

 harmon

-0.23

bable

-0.23

POSITIVE LOGITS

anders

0.33

åĪĨå¸ĥ

0.29

æ´ŀ

0.28

andro

0.26

ander

0.25

éĥĬ

0.24

andest

0.24

èħĲ

0.24

 distributing

0.24

 Distrib

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.