INDEX
Explanations
mentions of a specific person named "Fe"
the presence of the name "Fe" or variations of it
New Auto-Interp
Negative Logits
Carbuncle
-0.77
DOWN
-0.77
Nadu
-0.71
Columbia
-0.67
eleph
-0.67
GEAR
-0.66
Narr
-0.65
ANGEL
-0.63
uyomi
-0.62
MSI
-0.62
POSITIVE LOGITS
cking
1.06
lder
1.05
vered
1.05
els
1.02
ulner
1.00
elin
0.99
ck
0.97
plin
0.96
uth
0.94
eling
0.93
Activations Density 0.017%