INDEX
Explanations
financial and technical terms related to internet domain management
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1978
+0.13
0.4%
453
+0.11
0.4%
605
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1045
+0.13
0.04
605
+0.11
0.01
453
+0.11
0.04
Negative Logits
læng
-0.55
ddelweddau
-0.55
-0.53
tshirt
-0.48
norsk
-0.48
Solución
-0.47
siège
-0.46
tæt
-0.46
placée
-0.46
respawn
-0.46
POSITIVE LOGITS
kram
1.02
kafe
1.01
silikon
0.97
ananas
0.95
kokos
0.93
kristal
0.93
panik
0.92
adil
0.89
bera
0.89
optik
0.89
Activations Density 0.256%