INDEX
Explanations
references to health and safety measures, especially related to masks and smoking
New Auto-Interp
Negative Logits
ecess
-0.16
ivot
-0.15
.tc
-0.15
enefit
-0.15
.Ui
-0.15
adm
-0.14
Forum
-0.14
ùi
-0.14
echa
-0.14
ilon
-0.14
POSITIVE LOGITS
iyon
0.16
izr
0.15
arf
0.14
Ply
0.14
Lambert
0.14
Hib
0.14
culture
0.14
.Lib
0.14
perceived
0.14
ermen
0.14
Activations Density 0.015%