INDEX
Explanations
time-related entities such as days, weeks, months, and hours
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
776
+0.10
0.3%
490
+0.09
0.3%
1013
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1384
+0.10
0.05
1025
+0.09
0.04
490
+0.09
0.03
Negative Logits
Gep
-0.57
&___
-0.54
featureID
-0.53
Beit
-0.53
cydow
-0.51
Gnaden
-0.51
gatsby
-0.51
LookAnd
-0.51
webElementXpaths
-0.50
TabStop
-0.50
POSITIVE LOGITS
unwarran
0.85
pamph
0.82
ingrat
0.78
disagre
0.78
Shakspeare
0.74
McLaugh
0.70
Mónica
0.69
despotism
0.68
alnız
0.66
courtier
0.65
Activations Density 0.122%