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

æŁŀ

-0.27

ç¿»èº«

-0.27

å±ģèĤ¡

-0.26

æ²¹çĶ°

-0.25

baugh

-0.25

åĴ½åĸī

-0.25

è¹¶

-0.24

 resultMap

-0.24

closure

-0.24

flag

-0.24

POSITIVE LOGITS

raf

0.26

ufe

0.26

rote

0.26

ç¶ĵ

0.25

.split

0.24

ä¿®

0.24

ç»ı

0.24

ä½ĵ

0.24

(scale

0.24

ry

0.24

Activations Density 0.056%

No Known Activations

This feature has no known activations.