INDEX

Explanations

exponent and power laws

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

arnings

-0.77

 Myers

-0.76

 mileage

-0.71

 meditations

-0.71

 Gerard

-0.68

 McNeil

-0.65

Una

-0.64

ogo

-0.64

 мерт

-0.64

名の

-0.64

POSITIVE LOGITS

 exponent

4.34

 exponents

4.03

exponent

3.36

Exponent

3.02

 power

2.20

 powers

2.03

指数

1.96

power

1.96

 expo

1.95

 expon

1.94

Activations Density 0.081%