INDEX

Explanations

standing out from competition

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 konc

1.77

 thicker

1.70

中間

1.67

newer

1.56

 klass

1.51

 komfort

1.47

 einfache

1.44

펙

1.44

middle

1.43

klassen

1.43

POSITIVE LOGITS

of

1.30

ámica

1.29

ijska

1.28

γράφ

1.27

imli

1.26

 empec

1.23

explique

1.21

rú

1.21

 blur

1.21

魘

1.19

Activations Density 0.021%