INDEX
Explanations
chemical and medical terms related to specific conditions from patient records
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.20
0.6%
1150
+0.10
0.3%
2034
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1672
+0.20
0.03
1640
+0.10
0.02
279
+0.09
0.03
Negative Logits
shenan
-0.69
telah
-0.66
laug
-0.62
Să
-0.62
ējās
-0.60
outdir
-0.59
scound
-0.58
Și
-0.58
Junto
-0.58
fuckin
-0.58
POSITIVE LOGITS
lele
1.18
kasa
1.03
antik
1.02
hina
1.00
elek
0.99
kac
0.98
buk
0.98
fré
0.96
kupa
0.95
kram
0.95
Activations Density 0.108%