INDEX
Explanations
references to military equipment and operations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
270
+0.10
0.3%
939
+0.10
0.3%
604
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
939
+0.10
0.08
1997
+0.10
0.04
1499
+0.09
0.07
Negative Logits
<bos>
-0.71
feen
-0.64
paff
-0.61
reft
-0.59
!...
-0.58
juf
-0.58
laft
-0.57
?...
-0.56
beft
-0.56
pite
-0.55
POSITIVE LOGITS
Mérida
0.52
defense
0.52
defence
0.51
Cádiz
0.48
defensive
0.48
Concepción
0.47
Almería
0.47
виправивши
0.46
strategic
0.46
defensively
0.46
Activations Density 0.746%