INDEX

Explanations

non-

speech, translation, C++

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

讨厌

0.48

 unlawfully

0.46

进步

0.43

argu

0.43

빤

0.43

 자신의

0.42

ეგ

0.41

 месяца

0.41

 breastfeeding

0.41

が好き

0.40

POSITIVE LOGITS

()}

0.45

NON

0.44

construction

0.41

 phosphoric

0.40

遴

0.40

 regularization

0.40

setminus

0.40

)};

0.40

 internals

0.40

non

0.39

Activations Density 0.001%