INDEX
Explanations
references to a specific city's infrastructure projects and controversies
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1937
+0.16
0.6%
390
+0.14
0.5%
1133
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
390
+0.16
0.05
220
+0.14
0.05
1937
+0.12
0.05
Negative Logits
intersper
-0.80
shenan
-0.75
scrat
-0.74
snoopy
-0.72
wattpad
-0.72
guarante
-0.69
encomp
-0.69
ralph
-0.69
affor
-0.68
perfet
-0.67
POSITIVE LOGITS
city
1.38
city
1.29
City
1.29
City
1.28
CITY
1.12
CITY
1.11
cities
1.01
getCity
0.98
Cities
0.88
Cities
0.88
Activations Density 0.094%