INDEX

Explanations

quantities greater than

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

The

-2.22

-1.99

↵↵

-1.83

咔

-1.72

蹦

-1.69

 большого

-1.67

 męskie

-1.66

ǧ

-1.64

忙碌

-1.61

真好

-1.59

POSITIVE LOGITS

 than

3.16

ματος

2.13

卹

2.08

 importantly

2.05

銼

1.94

indrome

1.93

 convinced

1.92

 mayoría

1.91

謖

1.90

 rengi

1.88

Activations Density 0.010%