INDEX
Explanations
names of a specific person, "Kisser"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.13
0.4%
394
+0.09
0.3%
50
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1919
+0.13
0.08
227
+0.09
0.08
1097
+0.08
0.07
Negative Logits
Himo
-1.07
RectangleBorder
-0.93
poliester
-0.86
Walkover
-0.85
Unito
-0.85
matrimon
-0.83
lomb
-0.82
polig
-0.81
LUMP
-0.81
ló
-0.81
POSITIVE LOGITS
shenan
2.00
unspeak
1.89
disagre
1.88
impra
1.84
gaily
1.82
inappro
1.80
depic
1.79
reluct
1.78
encomp
1.78
maneu
1.77
Activations Density 0.597%