INDEX
Explanations
This neuron detects numeric and monetary expressions in budget‐ and finance‐related contexts (e.g. figures, percentages, dollar amounts, years).
New Auto-Interp
Negative Logits
asp
-0.07
Further
-0.07
Pedido
-0.07
(fm
-0.07
IFF
-0.06
weaker
-0.06
Ext
-0.06
Missing
-0.06
Member
-0.06
Chip
-0.06
POSITIVE LOGITS
�
0.07
.getItemId
0.07
tvrd
0.07
การเล
0.06
[]↵
0.06
lleg
0.06
.tabControl
0.06
Mining
0.06
.VERTICAL
0.06
praw
0.06
Activations Density 0.027%