INDEX

Explanations

numerical data and percentages

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

美國

-1.73

 lavable

-1.59

日発売

-1.56

();

-1.53

Біографія

-1.52

 Matéri

-1.45

४

-1.43

 PUSTAKA

-1.38

บริ

-1.37

tagext

-1.37

POSITIVE LOGITS

of

2.08

in

2.05

1.89

 overall

1.77

 first

1.73

 everyone

1.63

 something

1.59

 everything

1.58

 their

1.57

 today

1.54

Activations Density 0.048%