INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bodies
    0.50
     body
    0.49
     Body
    0.49
    身体
    0.48
     bodied
    0.47
     Bodies
    0.46
     BODY
    0.45
     بدن
    0.44
     tubuh
    0.44
    ボディ
    0.44
    POSITIVE LOGITS
    meta
    0.62
     meta
    0.55
    Meta
    0.55
    charset
    0.53
     Meta
    0.53
     charset
    0.52
    lang
    0.50
    Charset
    0.50
    META
    0.50
     META
    0.50
    Act Density 0.003%

    No Known Activations