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

 aster

-0.27

anggal

-0.26

éĵİ

-0.25

 sewing

-0.25

mou

-0.24

æĹ¶åħī

-0.24

è¾°

-0.24

@[

-0.24

aster

-0.24

çļĦè¡£æľį

-0.24

POSITIVE LOGITS

å¼Ľ

0.26

”

0.26

 tenth

0.26

èµģ

0.25

éķľ

0.25

ufs

0.23

.—

0.23

 consenting

0.23

ç§¯æŀģæİ¢ç´¢

0.23

kke

0.23

Activations Density 0.036%

No Known Activations

This feature has no known activations.