INDEX
Explanations
mentions of the city of Berlin
occurrences of the word "Berlin."
New Auto-Interp
Negative Logits
awaru
-0.75
heed
-0.73
sorcery
-0.71
Inqu
-0.65
snake
-0.65
induct
-0.64
plate
-0.64
************
-0.64
turtle
-0.62
umed
-0.62
POSITIVE LOGITS
Berlin
3.85
Frankfurt
2.09
Munich
2.09
Hamburg
2.00
Warsaw
1.98
Dresden
1.94
Budapest
1.91
Vienna
1.90
Prague
1.90
Germany
1.88
Activations Density 0.009%