INDEX
Explanations
sports-related terms such as player names and skills
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
394
+0.26
0.8%
856
+0.24
0.8%
764
+0.17
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
394
+0.26
0.07
764
+0.24
0.06
856
+0.17
0.05
Negative Logits
isenberg
-0.53
зулта
-0.50
ècie
-0.49
SourceChecksum
-0.48
patin
-0.46
dames
-0.46
bezeichneter
-0.45
ांकि
-0.45
afirm
-0.44
featureID
-0.44
POSITIVE LOGITS
chrysler
0.69
embodi
0.67
chevrolet
0.64
lamborghini
0.63
volkswagen
0.62
volkswagen
0.61
Dzięki
0.60
hilux
0.60
scrat
0.59
withal
0.59
Activations Density 0.684%