INDEX
Explanations
details related to mechanical parts and components
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1385
+0.22
0.7%
1343
+0.17
0.5%
906
+0.16
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.22
0.07
724
+0.17
0.05
1385
+0.16
0.05
Negative Logits
praktik
-1.24
pessi
-1.12
keramik
-1.07
Politica
-1.07
gend
-1.06
socie
-1.06
alkoh
-1.05
optik
-1.05
notor
-1.05
protokol
-1.05
POSITIVE LOGITS
człowie
0.58
width
0.56
amado
0.55
vertical
0.53
anzunehmen
0.53
readline
0.52
width
0.52
extends
0.52
edges
0.52
extend
0.52
Activations Density 0.351%