INDEX
Explanations
negative sentiments or critical phrases related to movement or occurrences
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.07
3:0.23
4:0.02
5:0.02
6:0.11
7:0.13
8:0.07
9:0.09
10:0.07
11:0.09
Negative Logits
Territories
-1.30
龍�
-1.22
Province
-1.17
anmar
-1.11
Trafford
-1.09
Ange
-1.08
soDeliveryDate
-1.06
魔
-1.05
�
-1.04
provinces
-1.02
POSITIVE LOGITS
ignition
1.22
candles
1.19
lamps
1.19
torches
1.18
combustion
1.07
ovsky
1.07
osi
1.05
rive
1.05
Â
1.05
[*]
1.04
Activations Density 0.003%