INDEX
Explanations
proper nouns or names related to sports teams or individuals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1557
+0.10
0.3%
161
+0.10
0.3%
492
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1120
+0.10
0.05
690
+0.10
0.05
1363
+0.09
0.04
Negative Logits
jeste
-0.65
tager
-0.62
findes
-0.61
مد
-0.60
larımız
-0.59
зидент
-0.59
paralleled
-0.59
participate
-0.58
receive
-0.58
oblotting
-0.57
POSITIVE LOGITS
Kn
1.95
Kn
1.77
kn
1.61
embra
1.48
effe
1.46
eiffel
1.46
campa
1.46
depic
1.44
accla
1.44
unden
1.43
Activations Density 0.317%