INDEX
Explanations
mentions of the word "Bl" followed by a high number
mentions of the name "Blatter."
New Auto-Interp
Negative Logits
Occupations
-0.86
OLOGY
-0.73
WATCH
-0.69
HER
-0.67
UAL
-0.67
IUM
-0.65
LER
-0.65
gerald
-0.62
Tags
-0.62
Seym
-0.61
POSITIVE LOGITS
itzer
1.28
anche
1.26
asts
1.15
ocking
1.13
adder
1.12
anco
1.10
ushing
1.08
anch
1.08
anches
1.05
asted
1.05
Activations Density 0.014%