INDEX
Explanations
dates mentioned as well as specific accomplishments
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.12
0.3%
674
+0.11
0.3%
1967
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
776
+0.12
0.05
535
+0.11
0.03
861
+0.11
0.04
Negative Logits
unwarran
-1.23
tolerably
-1.20
disagre
-1.16
gaily
-1.15
unspeak
-1.15
unlaw
-1.12
impractica
-1.12
apprehen
-1.11
hairc
-1.05
shewn
-1.04
POSITIVE LOGITS
geograf
0.68
Rektor
0.61
·
0.61
alkoh
0.60
Pfarr
0.59
republi
0.59
Jugos
0.59
ideolog
0.59
recipro
0.58
komment
0.58
Activations Density 0.205%