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

éĽĦ

-0.28

ĽĦ

-0.26

.dk

-0.25

zte

-0.25

èĭ±

-0.25

 Hurt

-0.25

oint

-0.24

orgh

-0.24

 Pearce

-0.24

gh

-0.23

POSITIVE LOGITS

 scrapped

0.29

 PROT

0.28

ä¾¨

0.25

æĻĴ

0.25

 instagram

0.25

æĹĭ

0.25

forme

0.24

éĥ½éĿŀå¸¸

0.24

 Bram

0.24

sus

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.