INDEX
Explanations
terms and phrases associated with gaming-related actions or descriptions
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.04
3:0.04
4:0.04
5:0.04
6:0.42
7:0.12
8:0.03
9:0.06
10:0.08
11:0.04
Negative Logits
ottest
-1.53
cules
-1.31
ufact
-1.31
ailability
-1.29
icago
-1.24
ebted
-1.23
phia
-1.23
Loyal
-1.22
votes
-1.20
skelet
-1.19
POSITIVE LOGITS
mir
1.42
etry
1.34
adder
1.34
meier
1.30
tsky
1.26
osi
1.23
Weaver
1.22
adders
1.21
ricks
1.20
irie
1.17
Activations Density 0.001%