INDEX
Explanations
text related to books, writing, and creation of stories
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1967
+0.20
0.7%
1984
+0.16
0.5%
1385
+0.14
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1984
+0.20
0.12
1967
+0.16
0.07
1896
+0.14
0.05
Negative Logits
tramonto
-1.22
medesimo
-1.16
paradiso
-1.01
mattino
-1.01
papà
-1.00
signore
-0.99
tempio
-0.99
hadur
-0.95
jaya
-0.94
lapin
-0.94
POSITIVE LOGITS
lot
0.69
Glej
0.65
person
0.64
particular
0.63
couple
0.63
few
0.62
Secara
0.62
Sebagai
0.61
Einen
0.59
Sklici
0.59
Activations Density 0.594%