INDEX
Explanations
chemical compounds related to acidity
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
410
+0.14
0.8%
230
+0.14
0.8%
327
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
111
+0.14
0.01
410
+0.14
0.01
3
+0.13
0.01
Negative Logits
else
-1.62
'</
-1.59
auc
-1.55
time
-1.52
else
-1.49
replaced
-1.44
oths
-1.43
normal
-1.39
Âł↵
-1.39
nominal
-1.39
POSITIVE LOGITS
ĻĤ
4.50
ŀ
3.77
¡
3.69
¥
3.64
¢
3.63
ģ
3.55
£
3.52
¿½
3.49
¨
3.48
Ĩ
3.38
Activations Density 0.009%