INDEX

Explanations

common words followed by punctuation

major spoilers ahead

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

0.47

 participants

0.46

 hints

0.44

 pudd

0.44

 Manifesto

0.44

 trivia

0.44

 pagination

0.43

 rewarded

0.43

 luminosity

0.43

POSITIVE LOGITS

ęs

0.54

瑢

0.50

 भै

0.49

Benzoimidazol

0.48

 vutto

0.48

amata

0.47

UpDown

0.46

memiş

0.46

𝑵

0.46

ی

0.46

Activations Density 0.000%