INDEX
Explanations
locations or spatial descriptions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1438
+0.13
0.4%
1437
+0.11
0.3%
674
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1437
+0.13
0.04
597
+0.11
0.03
1491
+0.11
0.04
Negative Logits
Denote
-0.55
benzyl
-0.53
Dimethyl
-0.49
methoxy
-0.48
('../../../-0.47
Corollary
-0.47
PageModule
-0.47
tcp
-0.46
THEOREM
-0.46
system
-0.45
POSITIVE LOGITS
aen
1.11
fta
1.01
poff
1.00
wherea
0.99
ftu
0.97
thut
0.96
mef
0.95
sergio
0.94
squa
0.93
uncin
0.93
Activations Density 0.123%