INDEX

Explanations

Forum posts and documentation

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

ç¡®

-0.27

æĭĽ

-0.26

éŁ¶

-0.26

ç§ĳ

-0.25

—

-0.25

 dele

-0.24

leÅŁ

-0.24

éĻĢ

-0.24

ãģ¹

-0.23

åĪ·æĸ°

-0.23

POSITIVE LOGITS

ittle

0.29

èĥ½åĬĽåĴĮ

0.28

 recoil

0.28

ughter

0.27

owell

0.26

lland

0.25

 retiring

0.25

udies

0.25

åı¯æİ§

0.25

æĿĵ

0.24

Activations Density 0.001%