INDEX

Explanations

errors, Lists, and array initialization

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

 could

-1.29

my

-1.29

رم

-1.16

ismen

-1.16

edy

-1.16

 encontramos

-1.15

푉

-1.15

 débris

-1.14

 tory

-1.13

koszulka

-1.13

POSITIVE LOGITS

 that

2.45

 with

1.34

 viena

1.29

issenschaft

1.27

."

1.24

not

1.23

ớp

1.23

 będziesz

1.22

(){

1.21

That

1.20

Activations Density 0.057%