INDEX
Explanations
Fraternity and sorority-related terms
references to specific fraternities and related terms
New Auto-Interp
Negative Logits
ocalypse
-0.69
stroke
-0.67
over
-0.67
Alz
-0.66
widget
-0.65
Homs
-0.64
lessly
-0.64
è¦ļéĨĴ
-0.63
Cyborg
-0.62
ouf
-0.60
POSITIVE LOGITS
Phi
1.24
ulty
1.14
uates
1.14
fraternity
1.06
umni
1.02
Sigma
1.01
ilon
1.00
atern
1.00
alum
0.99
ority
0.98
Activations Density 0.095%