INDEX
Explanations
references to location names, such as countries and states
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.10
0.3%
1967
+0.09
0.3%
1438
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1438
+0.10
0.05
284
+0.09
0.06
1013
+0.09
0.06
Negative Logits
aen
-1.63
fte
-1.61
dises
-1.56
inev
-1.55
effe
-1.54
emphat
-1.53
affor
-1.52
wherea
-1.52
fuf
-1.52
secon
-1.51
POSITIVE LOGITS
via
0.71
during
0.68
without
0.66
via
0.64
XMLSchema
0.63
">—
0.62
InitVars
0.61
FailureListener
0.60
webElementXpaths
0.59
from
0.59
Activations Density 0.373%