INDEX

Explanations

news categories

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

 refueling

-0.95

ู่

-0.79

 incarnate

-0.78

するために

-0.74

 officielles

-0.72

SCO

-0.72

"])

-0.72

authService

-0.71

]\\

-0.71

RSI

-0.70

POSITIVE LOGITS

 politics

1.66

 Politics

1.44

 lifestyle

1.31

Politics

1.30

politics

1.25

 Lifestyle

1.23

 sports

1.20

world

1.14

 world

1.13

 science

1.13

Activations Density 0.041%