INDEX
    Explanations

    family and children's activities

    New Auto-Interp
    Negative Logits
     dehuman
    0.46
    政治
    0.46
     volupt
    0.45
    0.43
     misused
    0.43
    ಲಾಗಿದೆ
    0.43
    igent
    0.43
    iritual
    0.42
    議論
    0.42
     willpower
    0.42
    POSITIVE LOGITS
     children
    1.46
     Kids
    1.41
     crianças
    1.39
     kids
    1.38
     Children
    1.38
     बच्चों
    1.37
     gyerek
    1.34
     niños
    1.31
     kinderen
    1.30
     bambini
    1.29
    Act Density 0.136%

    No Known Activations