INDEX

Explanations

Introduction sections or code snippets

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

oyer

-0.27

 Toys

-0.25

æĸ¯åŁº

-0.25

SAX

-0.25

 consc

-0.25

çŁ¶

-0.24

åıĺå½¢

-0.23

 UIBarButtonItem

-0.23

 ..."↵

-0.23

Ð¾Ð²Ð°Ð½Ð¸Ðµ

-0.23

POSITIVE LOGITS

kop

0.30

ula

0.29

ä¸Ģåī¯

0.29

æİ§èĤ¡

0.29

åĬ¨æĢģ

0.28

Kop

0.28

(draw

0.28

dra

0.27

cop

0.26

Tem

0.26

Activations Density 0.021%