INDEX

Explanations

string literal delimiters

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

 conster

-1.40

 火鍋

-1.36

 作り方

-1.35

 teras

-1.35

 logar

-1.34

他们

-1.31

 taget

-1.30

 perna

-1.30

Послед

-1.29

綃

-1.28

POSITIVE LOGITS

1.62

or

1.51

1.31

1.30

 gdyż

1.29

情形

1.24

 aanzien

1.23

1.19

niger

1.19

 αυτή

1.16

Activations Density 0.013%