INDEX

Explanations

punctuation and abbreviations

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

 őket

-1.48

૯

-1.38

фт

-1.36

 ilç

-1.32

だったが

-1.30

he

-1.30

 például

-1.25

 lehet

-1.25

 stel

-1.24

/***/

-1.22

POSITIVE LOGITS

we

1.48

 本店

1.33

 tatsächlich

1.30

 saranno

1.29

 succeeding

1.28

 اکنون

1.27

姈

1.24

 direc

1.23

 gän

1.23

鐃

1.22

Activations Density 0.005%