INDEX

Explanations

double or dual contexts

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

In

-1.30

众多

-1.27

It

-1.16

 There

-1.13

if

-1.12

 bekannten

-1.08

נוּ

-1.06

 Also

-1.05

になりたい

-1.05

or

-1.03

POSITIVE LOGITS

double

1.16

 ваших

1.16

 rapor

1.15

 marins

1.15

<bos>

1.15

 angusti

1.12

IVENESS

1.11

 serre

1.10

และ

1.08

 bestia

1.08

Activations Density 0.086%