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

thood

-0.29

å¹¶ä¸İ

-0.28

dos

-0.28

èĲ½åĲİ

-0.28

éħįåĲĪ

-0.27

å±ķå¼Ģ

-0.27

lg

-0.27

dg

-0.26

åĬĽ

-0.26

çºµåĲĳ

-0.26

POSITIVE LOGITS

 liking

0.28

 definit

0.26

,**

0.26

Trait

0.25

æµ£

0.25

 voluntary

0.25

 likes

0.24

 supern

0.24

 exclus

0.24

 Pang

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.