INDEX
Explanations
names of people with initials in a specific format, ending with a period
references to universities and educational institutions
New Auto-Interp
Negative Logits
264
-0.78
263
-0.78
udic
-0.77
262
-0.75
ãĤº
-0.74
Äĩ
-0.73
266
-0.73
ãĤ¦ãĤ¹
-0.69
Pablo
-0.68
pie
-0.68
POSITIVE LOGITS
h
1.26
H
1.24
HS
1.20
hw
1.18
hs
1.14
HT
1.12
Hu
1.11
HT
1.10
har
1.09
HK
1.09
Activations Density 0.586%