INDEX
Explanations
information regarding laws and regulations related to healthcare and reproductive rights
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1177
+0.13
0.4%
1553
+0.10
0.3%
394
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1553
+0.13
0.06
1275
+0.10
0.03
1255
+0.09
0.04
Negative Logits
frambo
-0.71
Sén
-0.64
chèvre
-0.60
pantal
-0.58
Messieurs
-0.58
Châ
-0.57
herbes
-0.57
Rois
-0.55
veau
-0.55
persil
-0.55
POSITIVE LOGITS
necesariamente
0.55
comply
0.53
minimum
0.52
Minimum
0.51
minimum
0.51
RectangleBorder
0.50
necessariamente
0.49
mandatory
0.47
CIUDAD
0.47
mandatory
0.46
Activations Density 0.336%