INDEX

Explanations

common nouns and adjectives

phrases ending in punctuation

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

 ذریع

0.57

 çünkü

0.55

ም።

0.55

 کی۔

0.53

했으며

0.52

했고

0.52

}^{*}$.

0.52

었고

0.52

जबकि

0.52

 असून

0.51

POSITIVE LOGITS

 thì

1.10

 فإن

1.10

 there

0.94

 maka

0.93

we

0.91

 they

0.83

则

0.79

it

0.75

，《

0.75

你会

0.75

Activations Density 2.052%