INDEX

Explanations

printed materials

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

John

-0.71

 paznok

-0.69

 John

-0.68

样式

-0.68

jogo

-0.67

 deem

-0.66

 dares

-0.66

ᠢ

-0.66

mascul

-0.66

gou

-0.66

POSITIVE LOGITS

 printing

1.73

 printed

1.57

 printer

1.52

 print

1.48

 inkjet

1.47

 printers

1.45

 Printing

1.43

Printing

1.38

Printed

1.36

 sublimation

1.35

Activations Density 0.032%