INDEX

Explanations

descriptive lists, choices

structured code listings

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

oflav

0.53

единенных

0.44

$)

0.40

哲

0.39

γκεκρι

0.39

 demonstrable

0.39

மிக

0.38

печат

0.38

毫不

0.38

 blinked

0.38

POSITIVE LOGITS

ک

0.54

 トレー

0.53

 équipe

0.52

가

0.51

팀

0.51

 จะ

0.50

ダ

0.50

for

0.49

 posisi

0.49

 permeates

0.49

Activations Density 0.000%