INDEX

Explanations

references to large or significant quantities or magnitudes

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

 huge

-1.23

huge

-1.20

Huge

-1.03

 Huge

-0.96

 HUGE

-0.83

 hugely

-0.67

 становника

-0.63

 énorme

-0.62

 enormous

-0.61

twimg

-0.59

POSITIVE LOGITS

 Massive

1.78

Massive

1.70

massive

1.66

 massive

1.57

 massively

1.18

 massiv

0.92

 masiva

0.59

 massif

0.58

RegressionTest

0.57

cadilly

0.56

Activations Density 0.004%