INDEX
Explanations
references to Pakistan, its army, officials, events, and related terms
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
795
+0.16
0.6%
1942
+0.13
0.4%
31
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
795
+0.16
0.03
1942
+0.13
0.02
849
+0.12
0.02
Negative Logits
maha
-0.62
mandal
-0.58
Thiru
-0.52
yaa
-0.51
Punj
-0.50
clos
-0.49
krishna
-0.48
mahar
-0.48
ahalli
-0.47
Pancha
-0.47
POSITIVE LOGITS
Pakistan
1.17
Pakistan
1.14
Châ
1.00
Pakistani
0.97
Marín
0.94
Darío
0.93
Mlle
0.92
Héctor
0.92
giovanni
0.91
Mejía
0.90
Activations Density 0.072%