INDEX
Explanations
references to non-profit organizations
New Auto-Interp
Negative Logits
978
-0.15
onic
-0.14
iate
-0.14
'icon
-0.14
fty
-0.14
.flat
-0.14
&M
-0.14
respects
-0.13
Ä
-0.13
.Companion
-0.13
POSITIVE LOGITS
profit
0.21
-profit
0.20
government
0.18
501
0.16
profit
0.15
governmental
0.15
partisan
0.15
çĩŁ
0.14
Profit
0.14
ong
0.14
Activations Density 0.018%