INDEX
    Explanations

    phrases indicating custody-related situations or arrests

    New Auto-Interp
    Negative Logits
    ugg
    -0.15
    ett
    -0.14
     Tic
    -0.14
    åħ¹
    -0.13
    วร
    -0.13
    re
    -0.13
    iz
    -0.13
    orp
    -0.13
     height
    -0.13
    mas
    -0.13
    POSITIVE LOGITS
     MetroFramework
    0.16
     ActionTypes
    0.16
    aleur
    0.15
    aub
    0.15
    adla
    0.15
     actionTypes
    0.14
     PureComponent
    0.14
    ennes
    0.14
    afa
    0.14
    olith
    0.14
    Act Density 0.264%

    No Known Activations