INDEX
Explanations
data-related attributes, particularly those associated with categories, measurements, or identifiers
Code, dates, or numbers within text
technical documentation snippets
New Auto-Interp
Negative Logits
abestanden
-0.78
ویکیآمباردا
-0.72
autorytatywna
-0.66
opérateur
-0.63
存于互联网档案馆
-0.63
σθαι
-0.63
löyty
-0.60
IMON
-0.60
NSCoder
-0.59
armour
-0.58
POSITIVE LOGITS
1.47
1.27
1.26
1.24
1.24
1.24
1.21
1.17
1.15
1.11
Activations Density 0.510%