INDEX
Explanations
numerical data related to computing benchmarks and performance
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.30
0.9%
690
+0.13
0.4%
1699
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
876
+0.30
-0.01
690
+0.13
0.02
1834
+0.10
0.03
Negative Logits
<bos>
-0.91
Palestina
-0.78
Independencia
-0.78
Biografi
-0.77
Créditos
-0.77
Juventud
-0.76
Antecedentes
-0.75
Palmar
-0.75
Biografía
-0.74
Fotografía
-0.73
POSITIVE LOGITS
impra
1.77
increa
1.76
maneu
1.72
disreg
1.71
encomp
1.68
shenan
1.65
impractica
1.63
scrat
1.62
depic
1.61
intermitt
1.61
Activations Density 0.351%