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

uff

-0.29

UFF

-0.28

 Lopez

-0.26

 Abed

-0.25

ä¼ĺåħĪ

-0.25

äº²

-0.24

 Ã¶de

-0.24

Jad

-0.24

ASH

-0.24

Attachment

-0.24

POSITIVE LOGITS

çģ«çĥ§

0.30

 disruption

0.27

åľ¨ä¸ĢæĹģ

0.26

åŃ©åŃĲçļĦ

0.25

è°°

0.24

toggleClass

0.24

_exit

0.24

éĶĻè¿ĩ

0.24

"),"

0.24

ling

0.23

Activations Density 0.013%

No Known Activations

This feature has no known activations.