INDEX
Explanations
descriptions of a particular product or technology
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1385
+0.17
0.5%
876
+0.15
0.4%
1403
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
678
+0.17
0.05
1385
+0.15
0.04
1984
+0.11
0.04
Negative Logits
pamph
-1.14
panik
-0.93
Keny
-0.92
theolog
-0.89
sovere
-0.88
revan
-0.88
Minang
-0.86
errone
-0.86
Abbé
-0.86
superintend
-0.85
POSITIVE LOGITS
triomphe
0.83
créateur
0.77
vété
0.72
compatible
0.71
héros
0.71
merveilleux
0.71
fameux
0.70
rassemble
0.69
producteur
0.68
célé
0.67
Activations Density 0.343%