INDEX
Explanations
terms related to military and defense affairs
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.16
0.6%
144
+0.15
0.6%
1137
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
144
+0.16
0.04
1778
+0.15
0.03
1137
+0.12
0.04
Negative Logits
indestru
-0.94
shenan
-0.88
inext
-0.84
catast
-0.80
infallib
-0.79
erad
-0.79
scrat
-0.78
incarcer
-0.77
ingrat
-0.77
maneu
-0.77
POSITIVE LOGITS
defense
1.35
defense
1.30
Defense
1.23
defence
1.22
Defense
1.18
defence
1.12
DEFENSE
1.08
Defence
1.05
Defence
0.96
defenses
0.96
Activations Density 0.063%