INDEX
Explanations
references to numerical quantities or amounts
New Auto-Interp
Negative Logits
첫
-0.50
Мексичка
-0.50
Vaata
-0.50
tagext
-0.49
borbo
-0.49
DockStyle
-0.49
inspector
-0.49
cerah
-0.47
scegliere
-0.47
あくまで
-0.47
POSITIVE LOGITS
amount
1.77
Amount
1.58
amounts
1.57
Amount
1.57
amount
1.54
AMOUNT
1.44
Amounts
1.34
AMOUNT
1.30
amounts
1.23
Amounts
1.20
Activations Density 0.129%