INDEX
Explanations
phrases that indicate dental topics or discussions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.19
1.1%
504
+0.13
0.7%
85
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
504
+0.19
0.03
460
+0.13
0.05
446
+0.11
0.04
Negative Logits
omers
-1.65
landers
-1.60
astics
-1.58
Malays
-1.56
uits
-1.56
Malaysia
-1.44
BPF
-1.43
ylum
-1.42
fra
-1.41
inese
-1.41
POSITIVE LOGITS
¬
2.11
°
2.05
Ļª
1.98
ĻĤ
1.84
ĥ
1.83
Ģ
1.79
Ħ
1.77
ª
1.76
Īĺ
1.76
¨
1.74
Activations Density 2.680%