INDEX

Explanations

Identifiers and code types

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

༷

-1.70

釓

-1.65

</h2>

-1.56

 quiera

-1.54

...(

-1.40

 Literally

-1.38

 perdió

-1.38

-1.37

↵↵

-1.36

但在

-1.36

POSITIVE LOGITS

the

2.11

 they

1.83

 whether

1.82

 bluza

1.79

หรือ

1.77

канал

1.75

 formules

1.63

 یا

1.57

some

1.55

และ

1.55

Activations Density 0.003%