INDEX
Explanations
names of doctors and their specializations
New Auto-Interp
Negative Logits
enville
-0.16
509
-0.16
944
-0.16
asket
-0.15
696
-0.15
woff
-0.15
473
-0.14
695
-0.14
507
-0.14
Sadd
-0.14
POSITIVE LOGITS
lesh
0.27
esh
0.22
endra
0.22
ender
0.22
inder
0.21
deep
0.20
indre
0.20
oday
0.19
Deep
0.19
udev
0.18
Activations Density 0.214%