INDEX
Explanations
mentions of specific individuals, particularly those with the name "Jerome" or related forms
New Auto-Interp
Negative Logits
ThroughAttribute
-0.55
SupportActionBar
-0.51
clearfix
-0.49
Majefty
-0.47
paravant
-0.46
suivants
-0.46
ujednoznacz
-0.45
SwitchCompat
-0.45
getDoctrine
-0.45
argint
-0.44
POSITIVE LOGITS
Jerome
2.50
Jerome
2.33
Jérôme
1.55
érôme
1.12
Hieronymus
0.80
Tyrone
0.74
Girolamo
0.56
Jér
0.55
Cedric
0.54
Bertram
0.53
Activations Density 0.002%