INDEX
Explanations
references to children and familial or societal issues
New Auto-Interp
Negative Logits
ÏĢλα
-0.17
æĹłçłģ
-0.15
zure
-0.15
swire
-0.14
-0.14
ovic
-0.14
etable
-0.14
اÙĦا
-0.14
ãĥªãĤ«
-0.14
quartered
-0.13
POSITIVE LOGITS
Sen
0.24
Sen
0.21
democr
0.20
Conservatives
0.20
Rep
0.19
sen
0.19
republic
0.18
Column
0.18
House
0.18
Republicans
0.18
Activations Density 0.157%