INDEX
Explanations
references to Warsaw and its related locations and institutions
New Auto-Interp
Negative Logits
گاÙĨ
-0.17
ær
-0.17
,[],
-0.16
ije
-0.16
reon
-0.16
ilar
-0.15
rium
-0.15
žen
-0.15
Cair
-0.14
indir
-0.14
POSITIVE LOGITS
ÅĤaw
0.27
z
0.25
awa
0.24
awy
0.23
aw
0.22
ch
0.21
staw
0.20
kie
0.20
acz
0.20
zew
0.20
Activations Density 0.013%