INDEX

Explanations

specific contexts and tools

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

 presenta

0.50

 पॉपुलर

0.48

andelier

0.47

鲐

0.47

restaurant

0.47

ണ്ഡ

0.45

དང་

0.45

کنندگان

0.45

roa

0.45

াবাদ

0.44

POSITIVE LOGITS

 inciting

0.47

 crude

0.43

 λά

0.43

 minced

0.43

気の

0.43

⁹

0.42

暧

0.42

 обез

0.42

다라고

0.42

证实

0.41

Activations Density 0.000%