INDEX

Explanations

for introducing examples

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

DRO

2.89

eid

2.79

𝐞

2.62

2.49

ަތ

2.47

 例文帳に追加

2.42

ிய

2.42

েব

2.42

 auspicious

2.41

 суу

2.39

POSITIVE LOGITS

(/^\

2.49

geom

2.38

이션

2.33

ervis

2.31

اً

2.30

atoon

2.29

odesk

2.28

㎞

2.27

("{

2.26

oted

2.24

Activations Density 0.923%