INDEX

Explanations

citation numbers and years

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

ございません

-1.48

衩

-1.48

らなかった

-1.43

َّ

-1.42

前から

-1.38

跟

-1.37

 sierp

-1.36

 utilizarse

-1.35

 کنید

-1.34

೪

-1.32

POSITIVE LOGITS

 encontr

1.77

the

1.70

<bos>

1.58

 more

1.52

 reempla

1.51

 desear

1.50

it

1.49

の良い

1.46

 such

1.45

Activations Density 0.030%