INDEX
Explanations
phrases related to political and legislative actions and changes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
453
+0.12
0.3%
184
+0.11
0.3%
674
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
453
+0.12
0.05
184
+0.11
0.01
907
+0.09
0.02
Negative Logits
.
-0.65
Климат
-0.58
;
-0.56
.\\
-0.55
().
-0.53
..
-0.50
。
-0.49
:
-0.49
...
-0.49
!
-0.48
POSITIVE LOGITS
:)))
0.95
waer
0.94
tucson
0.94
Ottobre
0.93
stockholm
0.93
scattata
0.90
dises
0.88
Settembre
0.88
lidl
0.87
Luglio
0.86
Activations Density 0.520%