INDEX

Explanations

drawing straight lines

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

shadowRadius

-0.82

paces

-0.82

 fill

-0.75

wain

-0.73

 radius

-0.73

fill

-0.71

hole

-0.71

ພ

-0.71

 литература

-0.71

正面

-0.70

POSITIVE LOGITS

 lines

2.88

 line

2.81

 Line

2.58

 Lines

2.36

Line

2.31

Lines

2.23

 LINE

2.19

 LINES

2.03

line

2.02

lines

1.97

Activations Density 0.056%