INDEX

Explanations

offensive or harmful content

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

 некоторых

-1.59

”(

-1.48

 rano

-1.40

somewhat

-1.40

 occuper

-1.37

 eſſ

-1.33

 завжди

-1.30

 Allemagne

-1.29

 alcuni

-1.27

 некоторы

-1.27

POSITIVE LOGITS

or

2.61

 или

1.98

或

1.72

 یا

1.59

有任何

1.55

または

1.45

 которая

1.43

 когда

1.41

したり

1.41

 других

1.36

Activations Density 0.063%