INDEX

Explanations

web urls and code

asking questions or giving commands

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

了一声

0.36

 asserted

0.36

 unwittingly

0.35

нодоро

0.34

“…

0.33

 unwitting

0.32

”…

0.32

Prevention

0.32

Heinrich

0.32

 overshadowed

0.31

POSITIVE LOGITS

usuario

0.56

contador

0.56

curso

0.54

prueba

0.53

texto

0.51

 Curso

0.51

tabla

0.49

projeto

0.49

codigo

0.49

carrito

0.49

Activations Density 0.003%