INDEX
Explanations
medical publication references with author names
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.28
0.9%
1741
+0.21
0.7%
16
+0.15
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.28
0.03
16
+0.21
0.03
1343
+0.15
0.03
Negative Logits
lørdag
-0.86
søndag
-0.86
chví
-0.84
VISIONS
-0.82
verstanden
-0.81
wspania
-0.80
kveld
-0.80
purplish
-0.80
zagro
-0.78
poważ
-0.78
POSITIVE LOGITS
Février
1.82
Kategor
1.73
Strukt
1.71
alkoh
1.61
Cfr
1.57
Lég
1.56
Traité
1.54
kosme
1.54
Leurs
1.52
Juillet
1.52
Activations Density 0.074%