INDEX
Explanations
information related to political figures and their health records
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1948
+0.10
0.3%
1356
+0.10
0.3%
1467
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1948
+0.10
0.06
1364
+0.10
0.04
861
+0.10
0.06
Negative Logits
swarovski
-1.21
hairc
-1.12
impractica
-1.10
embodi
-1.06
encomp
-1.06
indestru
-1.04
liberality
-1.01
disagre
-1.00
pollut
-0.99
ecru
-0.98
POSITIVE LOGITS
herself
0.94
herself
0.79
her
0.69
gynhyrchwyd
0.65
Demokrat
0.62
she
0.61
حياتها
0.61
Olympedia
0.59
Ukrain
0.58
ikon
0.57
Activations Density 0.528%