INDEX
Explanations
references to technical incidents and accidents involving machines
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1385
+0.15
0.5%
1842
+0.12
0.4%
906
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2044
+0.15
0.07
724
+0.12
0.05
324
+0.11
0.04
Negative Logits
inol
-0.70
dimenti
-0.69
pensi
-0.64
trovar
-0.64
allarg
-0.63
torner
-0.62
parteci
-0.62
perpé
-0.62
dimentic
-0.61
soprav
-0.60
POSITIVE LOGITS
ıldız
0.58
ATEGY
0.57
gusted
0.55
while
0.53
whilst
0.51
balkon
0.48
astrous
0.47
équipements
0.47
during
0.47
varm
0.47
Activations Density 0.532%