INDEX
Explanations
specific airline names and references to air travel
New Auto-Interp
Negative Logits
auer
-0.20
ftar
-0.15
Gibraltar
-0.14
etten
-0.14
Dodd
-0.14
rgan
-0.13
Compound
-0.13
eba
-0.13
Cod
-0.13
emma
-0.13
POSITIVE LOGITS
antas
0.16
ensem
0.15
operator
0.15
operator
0.15
arte
0.15
hem
0.14
.chart
0.14
ugin
0.14
.tc
0.14
ungs
0.14
Activations Density 0.036%