INDEX

Explanations

percentages of categories

versus or vs

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

 అనేక

0.47

atern

0.44

 няколко

0.44

𝓵

0.43

 toute

0.43

+:+

0.43

 چند

0.43

죄

0.43

 herkese

0.43

诛

0.42

POSITIVE LOGITS

 either

0.70

either

0.59

 varying

0.58

 outright

0.57

others

0.50

もしくは

0.50

$('#

0.49

合計

0.48

 others

0.48

 Others

0.48

Activations Density 0.088%