INDEX
Explanations
mentions of specific political terms and actions, specifically related to governmental cabinet meetings and decisions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1339
+0.16
0.7%
1961
+0.14
0.6%
544
+0.14
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
341
+0.16
0.03
544
+0.14
0.03
1339
+0.14
0.02
Negative Logits
perciò
-0.81
scrat
-0.80
encomp
-0.79
purtroppo
-0.79
anzi
-0.78
gild
-0.78
fortn
-0.77
unlaw
-0.76
increa
-0.75
pertanto
-0.75
POSITIVE LOGITS
cabinet
1.39
Cabinet
1.31
cab
1.20
cabinet
1.19
Cabinet
1.15
cabinets
1.14
Cab
1.10
CAB
1.06
Cab
1.03
cab
1.01
Activations Density 0.090%