INDEX
Explanations
descriptions related to military weaponry, specifications, and configurations, especially bombs and their classes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1385
+0.23
0.7%
876
+0.14
0.4%
1343
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1385
+0.23
0.05
297
+0.14
0.05
194
+0.10
0.02
Negative Logits
fromnode
-0.74
PerformLayout
-0.71
BeginInit
-0.69
脚注の使い方
-0.69
IsContent
-0.67
تانيه
-0.66
featureID
-0.64
QPalette
-0.63
Εκ
-0.62
jspb
-0.60
POSITIVE LOGITS
peppa
1.08
disreg
1.08
Juf
1.06
increa
1.05
pollut
1.02
fta
1.01
aen
1.01
lola
1.01
effe
1.00
fuf
0.99
Activations Density 0.419%