INDEX

Explanations

geometric shapes and modeling

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 algodão

-1.32

みたら

-1.32

tojas

-1.32

颪

-1.27



-1.25

 レー

-1.24

𝜖

-1.20

!");

-1.20

!";

-1.18

anego

-1.17

POSITIVE LOGITS

you

1.53

in

1.45

 with

1.43

 your

1.27

 २०

1.25

and

1.20

 during

1.17

it

1.16

 includes

1.13

at

1.13

Activations Density 0.049%