INDEX
Explanations
references to universities or educational institutions ("uni")
occurrences of the word "uni."
New Auto-Interp
Negative Logits
DOM
-0.68
sarc
-0.64
spons
-0.61
respectively
-0.60
lav
-0.60
smuggling
-0.59
break
-0.59
DOM
-0.58
plots
-0.58
events
-0.58
POSITIVE LOGITS
uni
4.76
hani
1.10
unin
1.09
iji
1.04
ubi
1.01
urai
0.98
uci
0.94
untu
0.92
udi
0.92
unda
0.92
Activations Density 0.043%