INDEX
Explanations
numbers and lists in a document
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
196
+0.10
0.3%
674
+0.10
0.3%
1387
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
645
+0.10
0.03
1023
+0.10
0.03
1183
+0.10
0.03
Negative Logits
Tecnologia
-0.51
COMPR
-0.47
melhor
-0.47
QtGui
-0.46
!("{-0.45
HttpPut
-0.45
chuckles
-0.45
Calidad
-0.45
Abbiamo
-0.44
Acab
-0.43
POSITIVE LOGITS
AMONG
1.03
among
0.92
among
0.89
Among
0.88
intersper
0.88
Amongst
0.88
tremb
0.87
Among
0.83
yong
0.80
amongst
0.79
Activations Density 0.059%