INDEX

Explanations

emergence from emptiness

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

泐

-1.61

⩕

-1.58

踯

-1.57

instead

-1.54

埽

-1.53

starting

-1.52

 новой

-1.50

ఽ

-1.48

Use

-1.48

am

-1.48

POSITIVE LOGITS

as

1.88

 from

1.77

are

1.52

 after

1.45

for

1.41

 शुर

1.38

ↀ

1.37

 This

1.32

 After

1.29

 provide

1.28

Activations Density 0.012%