INDEX
Explanations
mentions of New York City and its variations
New Auto-Interp
Negative Logits
ucci
-0.15
gether
-0.15
atur
-0.15
ä»¶
-0.15
era
-0.14
iday
-0.14
cco
-0.14
Ĥ¨
-0.14
itto
-0.14
ufs
-0.14
POSITIVE LOGITS
shire
0.21
City
0.17
flater
0.17
ans
0.17
/New
0.16
sik
0.16
ska
0.15
-based
0.15
наÑĤ
0.15
osten
0.14
Activations Density 0.030%