INDEX

Explanations

reporting official statements and announcements

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

BOTH

-1.70

章节错误

-1.55

our

-1.52

 zowel

-1.38

 caminhão

-1.34

哙

-1.31

 Baumwolle

-1.27

 Seventy

-1.24

だけではなく

-1.22

 både

-1.20

POSITIVE LOGITS

has

1.84

at

1.52

 after

1.30

してます

1.28

 first

1.25

 confirms

1.23

 have

1.23

 مكتبه

1.17

 appears

1.17

 from

1.17

Activations Density 0.078%