INDEX

Explanations

material from"}, "they started"}, "we can"}, "premium packages"}, "simplicity is"}

documentation role descriptions

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

žen

0.39

uding

0.39

 waarmee

0.39

нути

0.39

↵↵

0.37

ised

0.37

 которую

0.36

्रेडिट

0.36

 heißt

0.36

됐다

0.36

POSITIVE LOGITS

 utilice

0.50

They

0.45

 ისინი

0.45

 प्रत्येक

0.44

 또한

0.43

 모든

0.43

 यांचा

0.42

There

0.41

他们的

0.41

또한

0.41

Activations Density 0.231%