INDEX

Explanations

error messages and status levels

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

 with

-1.41

 like

-1.27

 through

-1.18

is

-1.16

 один

-1.14

 based

-1.13

 helped

-1.08

 тоже

-1.07

くれた

-1.03

 немного

-1.03

POSITIVE LOGITS

 clássico

1.38

ランダ

1.32

 BECAUSE

1.31

 Toshiba

1.28

aría

1.28

 erzielt

1.27

 melainkan

1.27

 guapos

1.26

 ícone

1.25

了一会儿

1.24

Activations Density 0.042%