INDEX
Explanations
attends to email domain tokens from their associated organizational names
New Auto-Interp
Head Attr Weights
0:0.09
1:0.11
2:0.09
3:0.04
4:0.05
5:0.02
6:0.06
7:0.49
Negative Logits
NameInMap
-0.43
springfox
-0.42
tonsoft
-0.41
$_['
-0.40
istocene
-0.38
dosi
-0.37
SequentialGroup
-0.36
awtextra
-0.35
parseColor
-0.34
+:+
-0.34
POSITIVE LOGITS
leman
0.43
istic
0.36
vulgaires
0.35
WSTR
0.35
Wnd
0.34
aceite
0.34
cional
0.34
...(
0.34
AST
0.33
亚
0.33
Activations Density 0.017%