INDEX
Explanations
mentions or discussions related to sexual assault
terms related to sexual assault and harassment
New Auto-Interp
Negative Logits
cit
-0.74
Econom
-0.72
selves
-0.72
SN
-0.70
peror
-0.69
flex
-0.68
çĦ
-0.67
hyper
-0.67
cannabin
-0.66
KC
-0.66
POSITIVE LOGITS
perpetrated
0.87
survivors
0.78
allegations
0.78
survivor
0.77
Rape
0.77
uality
0.76
victims
0.74
counselling
0.74
prevention
0.73
accusations
0.71
Activations Density 0.067%