INDEX
Explanations
details about specific events, especially related to investigations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.12
0.3%
1978
+0.10
0.3%
394
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
994
+0.12
0.03
1978
+0.10
0.04
886
+0.10
0.02
Negative Logits
erwähnten
-0.52
pymysql
-0.46
samlet
-0.46
moż
-0.46
mały
-0.44
manteau
-0.44
samoch
-0.44
wahre
-0.43
ductory
-0.43
pymongo
-0.43
POSITIVE LOGITS
lemp
0.86
monaster
0.85
alkoh
0.84
keramik
0.84
geograf
0.82
Kategor
0.82
utop
0.81
marte
0.80
akku
0.78
parati
0.78
Activations Density 0.213%