INDEX
Explanations
references to the phrase "die hard" or similar variations
the phrase "die hard."
New Auto-Interp
Negative Logits
arov
-0.69
iola
-0.66
acca
-0.65
MN
-0.65
Hilbert
-0.62
nesses
-0.60
NESS
-0.60
ORY
-0.60
ajo
-0.60
duration
-0.60
POSITIVE LOGITS
hard
1.23
getic
1.19
ffen
0.96
bold
0.93
horribly
0.88
hl
0.84
lect
0.81
Trying
0.77
simple
0.73
miser
0.72
Activations Density 0.043%