INDEX
Explanations
information related to Mexico, including locations, people, and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1233
+0.12
0.4%
11
+0.11
0.4%
812
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
973
+0.12
0.03
1654
+0.11
0.03
492
+0.11
0.03
Negative Logits
Darío
-1.30
Áng
-1.16
Cáceres
-1.13
Valentín
-1.11
Mejía
-1.11
Marín
-1.11
Lázaro
-1.09
Belén
-1.05
Cár
-1.04
Asunción
-1.04
POSITIVE LOGITS
Mexique
1.19
Mexico
1.15
mex
1.13
Mexico
1.12
Mex
1.10
Mexican
1.04
MEX
1.03
Mexican
1.02
carrefour
0.97
hina
0.95
Activations Density 0.108%