INDEX

Explanations

code and markup elements

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

 everything

-1.41

its

-1.39

 this

-1.35

 estadia

-1.29

}],

-1.27

のお知らせ

-1.25

なのかな

-1.25

 someone

-1.22

 ład

-1.20

 також

-1.20

POSITIVE LOGITS

は

1.22

1.19

そういった

1.16

 heridos

1.13

 ВИ

1.11

が

1.11

in

1.09

搅拌

1.08

ка

1.07

に

1.05

Activations Density 0.000%