INDEX
Explanations
mentions of specific names, activities, roles, and unique details about individuals or entities
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.21
0.7%
856
+0.15
0.5%
2015
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
50
+0.21
0.10
1013
+0.15
0.09
227
+0.13
0.09
Negative Logits
Wikisource
-0.71
utop
-0.71
indeb
-0.70
morfo
-0.70
fono
-0.69
logar
-0.65
revisor
-0.65
ideolog
-0.65
neum
-0.64
hipo
-0.63
POSITIVE LOGITS
shenan
1.20
unspeak
1.20
pamph
1.10
Shakspeare
1.10
gaily
1.09
reluct
1.07
indestru
1.07
apprehen
1.05
disagre
1.04
uninten
1.00
Activations Density 1.479%