INDEX
    Explanations

    references to specific locations

    New Auto-Interp
    Negative Logits
    __':
    -0.87
    __':
    
    -0.83
    resizingMask
    -0.71
    Personendaten
    -0.68
    featureID
    -0.67
     armour
    -0.66
    <?
    -0.66
    enapa
    -0.66
     parlour
    -0.65
    öszi
    -0.65
    POSITIVE LOGITS
     Indonesia
    0.81
    Indonesia
    0.77
     Indonesian
    0.75
    ONESIA
    0.69
    Jakarta
    0.69
     Indones
    0.64
     IDR
    0.63
     rupiah
    0.63
    polis
    0.61
     indonesia
    0.59
    Act Density 0.087%

    No Known Activations