INDEX

Explanations

path, stream, or line

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

 their

-1.95

Although

-1.59

Using

-1.56

 einzigen

-1.55

During

-1.54

While

-1.49

Most

-1.48

Before

-1.48

Unlike

-1.45

Like

-1.45

POSITIVE LOGITS

 včetně

1.84

1.52

&=&

1.45

 kemudian

1.43

ଃ

1.42

 ambiti

1.39

ieteur

1.38

 harden

1.37

 grumpy

1.37

 aggres

1.35

Activations Density 0.067%