INDEX
Explanations
terms related to holiday celebrations and events, particularly around Christmas and shopping
New Auto-Interp
Head Attr Weights
0:0.03
1:0.01
2:0.07
3:0.05
4:0.06
5:0.04
6:0.31
7:0.05
8:0.04
9:0.04
10:0.13
11:0.13
Negative Logits
enta
-1.36
neutrality
-1.23
66666666
-1.18
unicip
-1.18
amiya
-1.15
estern
-1.15
recomb
-1.14
decentral
-1.11
lucent
-1.11
tsky
-1.10
POSITIVE LOGITS
eve
1.22
iren
1.14
rences
1.11
ivari
1.07
Carnival
1.07
heat
1.06
Record
1.05
Catch
1.05
celebration
1.00
theme
1.00
Activations Density 0.013%