INDEX
Explanations
information related to travel
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
752
+0.15
0.5%
50
+0.12
0.4%
1334
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1334
+0.15
0.06
395
+0.12
0.05
161
+0.12
0.04
Negative Logits
móg
-0.76
OfYear
-0.66
będę
-0.63
ECTION
-0.60
proszę
-0.58
wiem
-0.58
ecuted
-0.58
widać
-0.58
zrobi
-0.58
ECONDS
-0.58
POSITIVE LOGITS
Souha
1.13
Bartholo
1.11
Juf
1.05
présidenti
0.98
simplif
0.94
Kün
0.93
Membre
0.93
Chá
0.92
Punj
0.91
Keny
0.91
Activations Density 0.218%