INDEX
Explanations
references to political movements or organizations
New Auto-Interp
Negative Logits
цездатний
-0.36
beautiful
-0.36
magnificent
-0.34
Himo
-0.33
enfans
-0.32
Guggenheim
-0.32
kå
-0.31
delivery
-0.31
reca
-0.31
};*/
-0.31
POSITIVE LOGITS
الحره
0.69
extremist
0.62
adherents
0.61
militant
0.60
extremism
0.58
createStatement
0.58
factions
0.55
ArgumentParser
0.55
faction
0.54
extremists
0.54
Activations Density 0.559%