INDEX
Explanations
mentions of political figures and their activities, especially related to international visits and interactions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
453
+0.09
0.3%
344
+0.08
0.2%
856
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1428
+0.09
0.04
1631
+0.08
0.04
81
+0.08
0.02
Negative Logits
hairc
-1.20
swarovski
-1.18
disreg
-1.06
Décembre
-1.04
scrat
-0.98
tupperware
-0.97
Février
-0.95
affez
-0.95
chèvre
-0.95
embodi
-0.93
POSITIVE LOGITS
visit
0.88
visiting
0.85
visits
0.82
visit
0.74
visited
0.74
Visiting
0.73
Visit
0.73
visiting
0.71
visita
0.70
Visit
0.67
Activations Density 0.363%