INDEX
Explanations
connections between social issues and their impacts on health and behavior
New Auto-Interp
Negative Logits
ervo
-0.18
ENA
-0.18
upy
-0.15
buz
-0.15
ctor
-0.15
duk
-0.14
koli
-0.14
ukan
-0.14
stein
-0.14
AXB
-0.14
POSITIVE LOGITS
bum
0.16
Ross
0.15
roat
0.14
.PO
0.14
/libs
0.14
wm
0.14
onic
0.14
ips
0.13
071
0.13
cott
0.13
Activations Density 0.121%