INDEX
Explanations
mentions of New Zealand and related entities or topics
New Auto-Interp
Negative Logits
Initialized
-0.71
itbart
-0.71
ãĥł
-0.68
ibilities
-0.65
aved
-0.64
<<
-0.64
bda
-0.63
Bat
-0.63
vez
-0.62
VALUE
-0.62
POSITIVE LOGITS
Zealand
1.11
XT
0.95
ers
0.94
Herald
0.88
Airways
0.88
Territories
0.86
Rugby
0.82
Instruments
0.80
Broadcasting
0.80
istani
0.79
Activations Density 0.019%