INDEX

Explanations

Formal/official contexts

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

 other

-0.31

åħ¶ä»ĸ

-0.29

èıĮ

-0.28

åħ¶å®ĥ

-0.27

åĬ¨ä½ľ

-0.27

plings

-0.27

ania

-0.27

å¾®

-0.26

ç§»åĬ¨

-0.25

.setParent

-0.25

POSITIVE LOGITS

omed

0.28

åĲĪæ³ķæĿĥçĽĬ

0.27

wright

0.25

é¸¥

0.25

crÃ©

0.25

 sunday

0.24

ogl

0.24

ä¸Ģèīĺ

0.24

æ©Ľ

0.24

LEM

0.24

Activations Density 0.002%