INDEX
Explanations
instances of waving or gestures of greeting and farewell
New Auto-Interp
Negative Logits
urent
-0.16
ongyang
-0.15
vez
-0.15
_sensitive
-0.15
½
-0.15
etri
-0.15
Matth
-0.14
/stdc
-0.14
iph
-0.14
<Date
-0.14
POSITIVE LOGITS
ripper
0.17
lessly
0.16
orra
0.15
ģn
0.15
Vect
0.15
ry
0.15
vais
0.14
riet
0.14
thứ
0.14
TN
0.14
Activations Density 0.031%