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

/hooks

-0.27

alien

-0.25

á»Ł

-0.25

tracker

-0.25

ãģ«ä¹Ĺ

-0.24

 ÄĳÃ´

-0.24

SITE

-0.24

æĿĲ

-0.24

 society

-0.23

ordo

-0.23

POSITIVE LOGITS

nost

0.31

Ã©v

0.28

åı¹æģ¯

0.27

 emphasis

0.26

 scarce

0.25

é¦ĸåıĳ

0.25

Ð¼ÐµÑī

0.25

é¡»

0.25

itize

0.24

atorium

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.