INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    0.55
    skine
    0.50
    шкин
    0.49
    イレ
    0.49
    quila
    0.48
     appointees
    0.48
    0.48
     breed
    0.47
     optics
    0.47
     restrained
    0.47
    POSITIVE LOGITS
     LGBTQ
    0.77
     gay
    0.68
     suicide
    0.68
     LGBT
    0.67
     Suicide
    0.66
     Rainbow
    0.65
     homophobic
    0.65
    LGBT
    0.62
     rainbow
    0.61
     Trevor
    0.61
    Act Density 0.039%

    No Known Activations