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

iscrim

-0.35

éķ¿çŁŃ

-0.27

åĽ½åľŁ

-0.26

æ´»åĬ¨ä¸Ń

-0.26

 Discrim

-0.26

.misc

-0.25

born

-0.25

åľ°ä¸Ń

-0.24

 Gear

-0.24

 Virt

-0.24

POSITIVE LOGITS

uez

0.25

xCF

0.24

sc

0.24

éĹ´æİ¥

0.24

éĻĲ

0.24

uelle

0.24

xcf

0.24

sez

0.24

strt

0.24

CBD

0.24

Activations Density 0.019%

No Known Activations

This feature has no known activations.