INDEX

Explanations

color schemes and combinations

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

-3.17

Because

-1.88

Despite

-1.77

Usually

-1.70

It

-1.69

That

-1.69

 Despite

-1.67

With

-1.64

 могут

-1.64

 hadapan

-1.63

POSITIVE LOGITS

2.30

⌵

1.62

 then

1.62

 hunne

1.56

 elbise

1.52

fekt

1.51

 klubben

1.46

 pantolon

1.44

阳台

1.44

plastik

1.41

Activations Density 0.004%