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

ä¸¾

-0.26

èĪī

-0.25

AK

-0.25

 Garrison

-0.24

åĨ³çŃĸ

-0.24

mmc

-0.23

buz

-0.23

 ÑģÐ¸ÑĤÑĥ

-0.23

æºŁ

-0.23

arrison

-0.23

POSITIVE LOGITS

chie

0.30

ç«ŀä»·

0.26

tility

0.25

ÂŃi

0.25

 batching

0.25

æ·¡

0.25

itage

0.24

å¯¹ä»ĺ

0.24

leh

0.24

weg

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.