INDEX
Explanations
mentions of individuals in official positions or appointments
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
453
+0.11
0.3%
344
+0.11
0.3%
1120
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
344
+0.11
0.04
1749
+0.11
0.06
453
+0.09
0.06
Negative Logits
hairc
-1.22
excru
-1.20
indestru
-1.12
impra
-1.11
ecru
-1.10
swarovski
-1.09
increa
-1.08
scrat
-1.06
disreg
-1.05
disagre
-1.05
POSITIVE LOGITS
resigned
0.69
tenure
0.69
appointed
0.63
resign
0.63
resignation
0.61
duties
0.58
overseeing
0.57
appointment
0.56
retiring
0.56
retirement
0.56
Activations Density 0.724%