INDEX

Explanations

code

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

 Pure

-0.29

çº¯åĩĢ

-0.27

Pure

-0.25

ELEMENT

-0.25

_invoke

-0.25

æĪĳå½ĵæĹ¶

-0.24

ëĭĪëĭ¤

-0.23

ut

-0.23

æĪĳè¿ĺ

-0.23

é¥

-0.23

POSITIVE LOGITS

ABL

0.26

æĪĸå°Ĩ

0.25

abbix

0.24

å¤ļä½ĻçļĦ

0.24

çļĦå·¨å¤§

0.24

.reverse

0.24

åĲ¦

0.24

 alternate

0.24

 travel

0.24

xbc

0.24

Activations Density 0.001%