INDEX
Explanations
administrative and financial irregularities and controversies
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1120
+0.10
0.3%
1948
+0.09
0.3%
604
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1948
+0.10
0.06
1519
+0.09
0.04
319
+0.08
0.04
Negative Logits
milf
-1.33
hairc
-1.30
indescri
-1.29
hentai
-1.26
disagre
-1.26
unspeak
-1.25
madonna
-1.24
increa
-1.21
broderie
-1.20
intersper
-1.19
POSITIVE LOGITS
taxpayers
0.85
taxpayer
0.82
expenditure
0.72
expenditures
0.72
spending
0.72
expense
0.71
expenses
0.68
expensive
0.68
cost
0.67
budget
0.65
Activations Density 0.665%