INDEX
Explanations
phrases referring to current times or popular trends
references to the current time period or contemporary trends
New Auto-Interp
Negative Logits
fect
-0.78
Hits
-0.77
acted
-0.75
idav
-0.75
umbn
-0.71
cohol
-0.67
anooga
-0.65
agus
-0.64
RTX
-0.63
ancial
-0.62
POSITIVE LOGITS
adays
0.90
days
0.82
hift
0.76
pring
0.76
onwards
0.75
dream
0.72
hops
0.70
abouts
0.70
forth
0.68
lights
0.66
Activations Density 0.017%