INDEX

Explanations

math and programming constructs

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

ּוֹ

-2.59

ֶּ

-2.25

ִּ

-2.11

ְּ

-2.00

ַּ

-1.95

 موبایل

-1.66

 آیفون

-1.62

 брюки

-1.60

 бампер

-1.54

וּ

-1.51

POSITIVE LOGITS

ׇ

2.41

 chré

1.89

 religieux

1.85

 النبات

1.74

ֺ

1.71

۟

1.67

֩

1.65

 الجلد

1.62

 ویتامین

1.60

ܐ

1.51

Activations Density 0.247%