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

heck

-0.27

ccb

-0.26

dest

-0.25

 fark

-0.25

arden

-0.25

sez

-0.24

æ·¡

-0.24

åĲĥä»Ģä¹Ī

-0.24

anner

-0.24

wf

-0.24

POSITIVE LOGITS

Ñĭ

0.28

ODB

0.26

 ÐĺÐ½ÑĤÐµÑĢ

0.25

éĩı

0.24

éĴŁ

0.24

 approx

0.23

Ã¤m

0.23

 quantity

0.23

Former

0.23

olders

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.