INDEX
Explanations
mentions of numbers accompanied by references to time in years
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.12
0.3%
2034
+0.11
0.3%
1013
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1830
+0.12
0.05
1962
+0.11
0.05
297
+0.10
0.05
Negative Logits
unlaw
-0.94
impractica
-0.89
javier
-0.87
bangkok
-0.85
chery
-0.81
scattata
-0.81
fernando
-0.80
rodriguez
-0.79
claudia
-0.79
sergio
-0.78
POSITIVE LOGITS
ago
0.62
since
0.54
.
0.53
технологий
0.53
now
0.49
herre
0.49
neté
0.48
VersionUID
0.48
;
0.46
MONTH
0.43
Activations Density 0.230%