INDEX
    Explanations

    information related to personal contact details

    New Auto-Interp
    Negative Logits
    enumi
    -0.65
    GRANTED
    -0.58
    featureID
    -0.55
    CreateModel
    -0.55
    XDECREF
    -0.53
    באנגלית
    -0.52
    >';
    
    -0.52
    ]');
    -0.51
    polizei
    -0.51
     int
    -0.51
    POSITIVE LOGITS
     kasarigan
    0.86
    MessageTagHelper
    0.66
     PLWABN
    0.62
     Adress
    0.59
     electrolux
    0.59
     COT
    0.58
     Rump
    0.58
     regency
    0.58
     Autre
    0.58
     HX
    0.58
    Act Density 0.150%

    No Known Activations