INDEX
Explanations
mentions of events or actions involving people or characters of different ages
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
596
+0.16
0.6%
795
+0.14
0.5%
1472
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
795
+0.16
0.04
1472
+0.14
0.04
596
+0.13
0.04
Negative Logits
DisplayMetrics
-0.55
ExtendWith
-0.50
ıyordu
-0.50
AndroidJUnit
-0.48
HasForeignKey
-0.48
đồ
-0.47
виправивши
-0.47
thiết
-0.46
mıştır
-0.46
Dienstag
-0.44
POSITIVE LOGITS
effe
1.10
paff
1.06
grati
1.04
stefan
1.03
emphat
1.01
fatis
1.00
aen
1.00
magis
0.98
meis
0.95
Cfr
0.94
Activations Density 0.086%