INDEX

Explanations

and

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

 therefore

-1.06

 thus

-0.96

 then

-0.94

 hence

-0.91

 subsequently

-0.90

 thereby

-0.88

 consequently

-0.88

rogens

-0.88

 will

-0.85

 also

-0.84

POSITIVE LOGITS

 blessés

0.76

 vœux

0.73

 traités

0.70

 siècles

0.69

 nemlig

0.69

 oreilles

0.69

 épaules

0.68

 pères

0.68

 églises

0.67

 lèvres

0.66

Activations Density 0.021%