INDEX

Explanations

parenthetical abbreviations and citations

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

 these

-1.70

 when

-1.54

 kerana

-1.43

 çünkü

-1.42

 many

-1.38

 mostrarán

-1.38

 ayudan

-1.37

 their

-1.37

 each

-1.34

 comienzan

-1.34

POSITIVE LOGITS

and

2.42

of

1.30

もありますが

1.27

nze

1.27

 วาด

1.26

/***

1.25

as

1.25

nterior

1.24

 también

1.21

1.18

Activations Density 0.555%