INDEX
Explanations
the pronoun "he" indicating mentions of a specific male individual
New Auto-Interp
Negative Logits
1024
-0.62
Wizards
-0.61
PHI
-0.58
EB
-0.56
LDL
-0.55
EMP
-0.55
802
-0.54
Assassins
-0.54
acre
-0.54
Eleven
-0.54
POSITIVE LOGITS
ctic
0.89
aped
0.87
cation
0.81
aling
0.81
avier
0.79
redit
0.79
aded
0.77
ctor
0.77
uristic
0.77
arks
0.74
Activations Density 0.225%