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

vised

-0.29

Rub

-0.27

 lest

-0.27

lest

-0.27

åĵ®

-0.26

Scale

-0.25

 Coleman

-0.25

åı®

-0.25

 ÑĢÑĥÐ±

-0.24

è¦ģåĬłå¼º

-0.23

POSITIVE LOGITS

áº¡n

0.26

ãģĭãģĳãģ¦

0.25

mts

0.24

uppies

0.24

hips

0.23

rypt

0.23

-------↵

0.23

 dozen

0.23

acht

0.23

 terse

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.