INDEX
Explanations
references to individuals occupying public roles or positions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1490
+0.07
0.2%
1042
+0.07
0.2%
1533
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1181
+0.07
0.04
1509
+0.07
0.04
171
+0.07
0.04
Negative Logits
smtplib
-0.83
pymysql
-0.76
heapq
-0.73
ftu
-0.71
teras
-0.69
skimage
-0.65
zipfile
-0.65
jati
-0.64
thut
-0.64
obfer
-0.63
POSITIVE LOGITS
charisma
0.65
ardom
0.62
popularity
0.58
fame
0.57
charismatic
0.52
popularity
0.51
notoriety
0.50
livion
0.48
persona
0.48
Popularity
0.47
Activations Density 0.769%