INDEX

Explanations

separators `::` and `>>`

avoiding harm and violence

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ﺭ

0.55

}:{

0.54

 urmă

0.51

 அடிகள்

0.51

URNIZOR

0.50

૬

0.50

 ভাষায়

0.48

 подряд

0.47

 размер

0.47

 किरणों

0.47

POSITIVE LOGITS

if

0.43

ggg

0.42

특히

0.42

goài

0.40

또한

0.40

 även

0.40

 EVERY

0.40

vou

0.40

껍

0.40

تنا

0.39

Activations Density 0.001%