INDEX
Explanations
words related to products and their features
New Auto-Interp
Head Attr Weights
0:0.06
1:0.03
2:0.11
3:0.09
4:0.06
5:0.14
6:0.09
7:0.05
8:0.09
9:0.09
10:0.11
11:0.03
Negative Logits
mediation
-1.16
tut
-1.07
downstream
-1.06
Entered
-1.04
frivol
-1.00
Investig
-0.98
surrog
-0.98
unanim
-0.97
ba
-0.96
alleg
-0.96
POSITIVE LOGITS
malink
1.24
(?,
1.23
atus
1.18
ovie
1.15
MSN
1.13
orea
1.10
Topics
1.10
Featuring
1.09
III
1.08
unker
1.08
Activations Density 0.448%