INDEX
Explanations
references to individuals with the title "Prof."
references to professors and individuals with the title "Prof."
New Auto-Interp
Negative Logits
arrell
-0.77
eday
-0.71
aden
-0.69
eal
-0.69
tug
-0.69
allo
-0.69
iggins
-0.68
ingham
-0.66
diaper
-0.64
amas
-0.64
POSITIVE LOGITS
Prof
3.91
Prof
3.03
prof
2.46
Professor
1.93
Professor
1.69
prof
1.65
Dr
1.29
professor
1.21
professors
1.17
Stud
1.15
Activations Density 0.017%