INDEX
Explanations
exploited children and danger
New Auto-Interp
Negative Logits
Filosof
0.51
filozof
0.50
Philosophical
0.47
Himalayas
0.46
Himalayan
0.46
哲学
0.46
Atoms
0.44
Fault
0.44
Bauhaus
0.44
thérapeutique
0.43
POSITIVE LOGITS
police
1.02
police
0.98
crime
0.98
पुलिस
0.96
polícia
0.90
警方
0.89
crime
0.88
경찰
0.88
crimes
0.87
पुलिस
0.85
Activations Density 0.081%