INDEX
Explanations
references to locations or aspects of a city
New Auto-Interp
Negative Logits
aub
-0.18
Troll
-0.17
ullo
-0.16
.framework
-0.16
aber
-0.15
troll
-0.15
structuring
-0.15
بÛĮر
-0.15
trl
-0.14
omu
-0.14
POSITIVE LOGITS
Venice
0.36
Ven
0.35
Ven
0.33
ven
0.28
Venez
0.24
venez
0.23
Dog
0.23
Laguna
0.21
VEN
0.20
mainland
0.19
Activations Density 0.037%