INDEX
Explanations
instances of the concept of division or disagreement
references to division or disagreement between groups or entities
New Auto-Interp
Negative Logits
ECH
-0.71
oken
-0.69
Fargo
-0.68
ORTS
-0.66
OD
-0.66
jamin
-0.64
CHA
-0.64
elin
-0.64
queue
-0.63
psc
-0.63
POSITIVE LOGITS
divided
0.95
divides
0.84
naire
0.84
rescent
0.83
divisions
0.78
Split
0.77
iple
0.76
unequ
0.76
divide
0.76
escription
0.75
Activations Density 0.019%