INDEX

Explanations

the word "shadow"

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

 Swine

-0.66

Buk

-0.65

 swine

-0.64

rxjs

-0.63

 Lait

-0.63

Lep

-0.63

 trhu

-0.61

Kaynakça

-0.61

nehå

-0.60

 skimage

-0.60

POSITIVE LOGITS

 shadow

1.80

 Shadow

1.67

 shadows

1.66

shadow

1.60

 SHADOW

1.52

hadow

1.48

shadows

1.48

Shadow

1.45

SHADOW

1.43

 Shadows

1.32

Activations Density 0.004%