INDEX
Explanations
prepositional phrases starting with "of."
phrases indicating comparisons or quantities
New Auto-Interp
Negative Logits
merce
-0.69
guiActiveUn
-0.68
pta
-0.61
confir
-0.55
withd
-0.55
tsky
-0.54
TOP
-0.52
Bridges
-0.52
months
-0.52
Referred
-0.51
POSITIVE LOGITS
course
0.87
course
0.81
icial
0.69
substance
0.65
these
0.64
ussian
0.63
us
0.62
anything
0.62
iggle
0.61
theirs
0.60
Activations Density 0.099%