INDEX

Explanations

many

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

 nakalista

-0.73

 varandra

-0.73

 enfans

-0.71

 chré

-0.71

TestingModule

-0.68

 profondeur

-0.67

 morire

-0.66

 vitesses

-0.65

 profondità

-0.63

 feroit

-0.63

POSITIVE LOGITS

 plenty

0.81

 various

0.81

various

0.72

set

0.71

 lots

0.68

lot

0.67

Various

0.64

ver

0.64

 Various

0.63

 large

0.62

Activations Density 0.000%