INDEX
Explanations
stating or indicating existence
New Auto-Interp
Negative Logits
aquela
0.83
ニング
0.83
questão
0.82
aquell
0.82
göstere
0.79
těch
0.79
もの
0.77
nsan
0.77
那个
0.76
ọt
0.76
POSITIVE LOGITS
they
1.65
presence
1.51
displeasure
1.42
superiority
1.39
existence
1.37
наличие
1.33
adanya
1.33
наличи
1.32
intent
1.31
theyre
1.30
Activations Density 0.522%