INDEX

Explanations

javascript module imports

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

by

-2.31

してくれた

-1.63

had

-1.60

-1.55

中です

-1.51

理由は

-1.47

 tendría

-1.46

していて

-1.46

or

-1.41

has

-1.40

POSITIVE LOGITS

 that

2.33

镡

1.66

phoned

1.61

<bos>

1.60

 thofe

1.55

豳

1.48

⬈

1.46

folgen

1.46

 illi

1.45

 belang

1.45

Activations Density 0.027%