INDEX
Explanations
proper names, specifically the name "Zach"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
241
+0.19
1.1%
1757
+0.16
0.9%
31
+0.15
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.19
0.07
690
+0.16
0.04
1097
+0.15
0.06
Negative Logits
CROSSTALK
-0.63
Hunter
-0.59
%\[
-0.56
<bos>
-0.56
wpi
-0.56
crystal
-0.55
HasForeignKey
-0.55
Coo
-0.55
Pea
-0.54
Crystal
-0.53
POSITIVE LOGITS
territo
1.16
mef
1.07
myn
1.04
perfon
1.00
paff
1.00
bangkok
0.99
vns
0.99
naer
0.98
santiago
0.98
fup
0.98
Activations Density 0.766%