INDEX

Explanations

speaking or discussing text

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

-1.86

やってる

-1.75

ation

-1.74

すっ

-1.73

ーーーー

-1.73

明日は

-1.71

ings

-1.69

ang

-1.68

可以用

-1.68

POSITIVE LOGITS

and

1.90

臜

1.87

iyle

1.83

 listop

1.80

São

1.71

 trovato

1.67

minde

1.66

VGA

1.66

navn

1.60

我们

1.59

Activations Density 0.001%