INDEX
Explanations
mentions of geopolitical events and resolutions related to a specific location
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
604
+0.10
0.3%
1499
+0.10
0.3%
939
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1499
+0.10
0.07
939
+0.10
0.06
81
+0.09
0.03
Negative Logits
funko
-0.97
matel
-0.97
pixar
-0.93
edp
-0.87
chèvre
-0.87
vhs
-0.87
vété
-0.85
Docteur
-0.84
emphat
-0.84
pikachu
-0.84
POSITIVE LOGITS
international
0.74
multilateral
0.71
internacional
0.66
الدولى
0.62
international
0.62
International
0.61
diplomats
0.60
global
0.60
ziná
0.59
International
0.59
Activations Density 0.532%