INDEX
Explanations
technical terms related to physics, such as "gravity waves," "acoustic waves," and "compressibility."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.24
0.8%
1385
+0.14
0.4%
2015
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.24
0.06
876
+0.14
-0.01
724
+0.10
0.04
Negative Logits
Republi
-0.91
kriminal
-0.87
akut
-0.87
Immig
-0.86
Legislat
-0.86
kompati
-0.83
Komun
-0.82
kooper
-0.81
Demokrat
-0.80
republi
-0.80
POSITIVE LOGITS
swarovski
0.88
ecru
0.80
tricot
0.79
péché
0.75
broderie
0.72
malheur
0.72
stefan
0.71
startX
0.70
megane
0.69
chèvre
0.68
Activations Density 0.441%