INDEX
Explanations
percentage values and numerical proportions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1042
+0.14
0.4%
674
+0.12
0.4%
1967
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1526
+0.14
0.04
1304
+0.12
0.04
1596
+0.11
0.03
Negative Logits
futbolista
-0.62
comuna
-0.61
EEU
-0.61
;;)
-0.59
astéro
-0.56
álbum
-0.56
:,,
-0.55
letterSpacing
-0.55
LookAnd
-0.55
calciatore
-0.54
POSITIVE LOGITS
total
0.54
the
0.52
what
0.49
its
0.49
posób
0.48
archivio
0.48
êtres
0.47
their
0.45
Total
0.44
Total
0.44
Activations Density 0.125%