INDEX

Explanations

describing items or events

foundations and mapping

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

 meals

0.53

 kock

0.47

 spoons

0.45

 grundsätzlich

0.45

at

0.44

কম

0.44

 accompan

0.44

 multipl

0.43

 parsley

0.43

steins

0.42

POSITIVE LOGITS

 ער

0.51

0.50

㳓

0.49

Vaterpolo

0.48

 פרו

0.48

 因为

0.46

Hs

0.45

OHAMA

0.45

чения

0.45

VALUE

0.45

Activations Density 0.000%