INDEX
Explanations
numerical data related to publications
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.23
1.2%
874
+0.13
0.7%
1978
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
776
+0.23
0.05
874
+0.13
0.05
1978
+0.13
0.05
Negative Logits
<bos>
-2.16
GetKeyDown
-0.73
GEBURTSDATUM
-0.72
protoimpl
-0.72
ViewFeatures
-0.70
nahilalakip
-0.69
execSQL
-0.66
Diweddarwch
-0.66
ProtoMessage
-0.65
serangga
-0.65
POSITIVE LOGITS
increa
1.31
impra
1.30
affor
1.27
unlaw
1.27
reluct
1.23
Intere
1.23
maneu
1.20
disagre
1.17
suscep
1.16
Keny
1.16
Activations Density 0.087%