INDEX
Explanations
phrases related to travel and technology
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
658
+0.17
0.5%
381
+0.11
0.3%
478
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
658
+0.17
0.07
1919
+0.11
0.04
47
+0.11
0.04
Negative Logits
provoque
-0.84
viendra
-0.73
moza
-0.72
hej
-0.69
balon
-0.68
kac
-0.67
kask
-0.67
remonte
-0.66
utop
-0.66
karton
-0.65
POSITIVE LOGITS
xxii
0.67
xxv
0.67
interested
0.67
ryzen
0.66
unsure
0.66
xxvi
0.66
Jeśli
0.64
able
0.64
Eğer
0.64
LEGGI
0.63
Activations Density 0.152%