INDEX
Explanations
locations associated with military bases
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
281
+0.20
0.8%
597
+0.13
0.5%
479
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
281
+0.20
0.03
67
+0.13
0.02
597
+0.12
0.02
Negative Logits
igény
-0.45
зыка
-0.43
يكن
-0.43
자동
-0.42
Warwickshire
-0.42
mistak
-0.41
unemployed
-0.41
sistency
-0.41
tudom
-0.41
zieży
-0.41
POSITIVE LOGITS
Fort
1.47
Fort
1.45
FORT
1.26
fort
1.20
Forts
1.15
FORT
1.10
fort
1.07
forts
1.03
Ft
0.96
exé
0.92
Activations Density 0.104%