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

çļĦè¡¨çİ°

-0.26

åľ³

-0.25

 fairness

-0.25

 ingen

-0.25

agne

-0.24

ç»Ī

-0.24

åĨįåİ»

-0.24

è®¤

-0.24

á»Ĩ

-0.24

val

-0.23

POSITIVE LOGITS

ç±½

0.32

pg

0.26

occ

0.25

è¹¼

0.24

æĹĹ

0.24

æĮģèĤ¡

0.24

pto

0.24

ä¸Ńåħ³

0.23

lds

0.23

umni

0.23

Activations Density 0.009%

No Known Activations

This feature has no known activations.