INDEX
Explanations
database and API related commands and parameters
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
17
+0.29
1.7%
72
+0.15
0.9%
419
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
17
+0.29
0.05
72
+0.15
0.06
82
+0.14
0.05
Negative Logits
ĩ
-2.60
ľĵ
-2.55
ı
-2.49
ĥ
-2.45
ľ
-2.37
IJ
-2.33
Ĥ
-2.33
©
-2.29
ĸ
-2.24
Ĭ
-2.23
POSITIVE LOGITS
gage
1.62
ifice
1.57
fony
1.52
bench
1.51
expires
1.47
pload
1.41
reon
1.38
insula
1.38
eenth
1.31
verte
1.31
Activations Density 0.560%