INDEX

Explanations

Cour

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pic

-0.69

 free

-0.63

 Buch

-0.62

et

-0.59

 book

-0.58

 Book

-0.57

est

-0.56

Pic

-0.55

av

-0.54

POSITIVE LOGITS

 feroit

0.86

 énergé

0.85

AndEndTag

0.81

 étoient

0.79

 pouvoit

0.79

 vectorielles

0.78

 ainfi

0.77

 auroit

0.77

 démocr

0.76

 regeringen

0.75

Activations Density 0.228%