INDEX
Explanations
terms related to heart health and medical studies
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
308
+0.14
0.8%
156
+0.14
0.7%
59
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
59
+0.14
-0.01
92
+0.14
0.02
221
+0.13
0.00
Negative Logits
HN
-1.71
ared
-1.46
tmp
-1.44
npmjs
-1.43
/~
-1.41
apshot
-1.40
widened
-1.40
depended
-1.38
PLIED
-1.38
voted
-1.36
POSITIVE LOGITS
Ŀ
3.52
®
3.36
Ģ
3.33
ij
3.24
«
3.23
ª
3.12
Ĥ
3.11
°
3.09
ľ
3.07
ķ
3.04
Activations Density 1.470%