INDEX

Explanations

code components and markup

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

</h2>

-2.28

毉

-1.85

ſam

-1.77

 مشارکت‌کنندگان

-1.74

 ویکی‌پدیا

-1.74

شمار

-1.73

ୈ

-1.68

铁

-1.67

any

-1.66

渡し

-1.63

POSITIVE LOGITS

2.89

2.23

vantaged

2.19

<blockquote>

2.11

The

2.02

秶

1.89

 كما

1.88

</sub>

1.84

 また

1.77

って

1.69

Activations Density 0.003%