INDEX

Explanations

and

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

çļĦæĪĲæľ¬

-0.30

lope

-0.27

[mask

-0.26

ensis

-0.26

 dÃły

-0.25

æ·¡æ·¡çļĦ

-0.25

-html

-0.25

/post

-0.24

é«ĺä½İ

-0.24

çĸ«æĥħ

-0.23

POSITIVE LOGITS

äºĮçº§

0.34

ä¹Łåľ¨

0.28

ä¹Ł

0.27

ä¹Łè¢«

0.27

ä¸īçº§

0.27

ä¹Łæĺ¯ä¸Ģä¸ª

0.27

ä¸Ģçº§

0.26

 integr

0.26

 included

0.25

anded

0.25

Activations Density 0.003%