INDEX

Explanations

contour lines

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

taxon

-0.80

 recette

-0.75

ulsions

-0.73

itars

-0.72

得点

-0.71

 coder

-0.71

Suns

-0.68

 giggles

-0.67

TokenNameR

-0.66

AKP

-0.66

POSITIVE LOGITS

 contour

3.23

 contours

3.22

contour

2.91

Contour

2.66

contours

2.64

Contours

2.55

 Contour

2.44

 Cont

1.90

iso

1.89

 isother

1.70

Activations Density 0.028%