INDEX
Explanations
references to food preparation and nutritional information
New Auto-Interp
Negative Logits
tiener
-0.20
deen
-0.16
meisjes
-0.16
eskort
-0.15
whose
-0.15
whose
-0.15
_sz
-0.14
ipa
-0.14
gorith
-0.14
BorderStyle
-0.14
POSITIVE LOGITS
.nl
0.38
Dutch
0.36
Amsterdam
0.28
Rotterdam
0.27
NL
0.27
Netherlands
0.25
Gron
0.25
iteit
0.24
Nederland
0.24
_nl
0.24
Activations Density 0.320%