INDEX
Explanations
numerical quantities mentioned in a text
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1994
+0.11
0.3%
971
+0.10
0.3%
1535
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1994
+0.11
0.03
1
+0.10
0.04
220
+0.10
0.03
Negative Logits
Sén
-0.53
Karang
-0.50
Flamengo
-0.50
Olimpia
-0.50
Tahu
-0.49
Piso
-0.48
Levante
-0.48
palla
-0.47
Palmeiras
-0.47
Rossa
-0.47
POSITIVE LOGITS
number
0.82
number
0.76
Number
0.67
Number
0.65
NUMBER
0.65
NUMBER
0.62
ValueStyle
0.61
PerformLayout
0.60
getNumber
0.59
número
0.56
Activations Density 0.059%