INDEX

Explanations

code structure and parameters

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

\{

-2.88

⧠

-2.69

 представители

-2.67

-"

-2.63

,"

-2.45

 hermosas

-2.44

튿

-2.42

簠

-2.36

actéristi

-2.36

POSITIVE LOGITS

”

3.55

With

2.77

 seems

2.73

”,

2.64

To

2.56

For

2.48

’

2.31

or

2.31

The

2.30

2.28

Activations Density 0.009%