INDEX
Explanations
mentions of philanthropic activities and monetary grants in relation to charitable organizations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
964
+0.18
0.6%
1343
+0.16
0.6%
764
+0.16
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
764
+0.18
0.04
239
+0.16
0.04
81
+0.16
0.01
Negative Logits
<bos>
-0.69
organza
-0.59
twill
-0.52
jacquard
-0.49
velour
-0.48
bénéficiaire
-0.48
😍😍
-0.46
TECHNIQUES
-0.45
stoneware
-0.45
partenaire
-0.44
POSITIVE LOGITS
Keny
0.80
Lycée
0.77
Khart
0.72
Abbé
0.72
Luxem
0.71
ideolog
0.71
Reichstag
0.71
Heeren
0.71
Municip
0.70
kritis
0.69
Activations Density 0.442%