INDEX
    Explanations

    terms related to domestic violence and legal proceedings

    New Auto-Interp
    Negative Logits
    ={()=>
    -0.57
     خارجية
    -0.48
     inoc
    -0.46
     patriotism
    -0.45
    holung
    -0.44
     Foundry
    -0.43
    phrine
    -0.43
    CALLBACK
    -0.43
     purch
    -0.43
     isInitialized
    -0.43
    POSITIVE LOGITS
    AsUp
    0.97
     divorce
    0.95
     divorced
    0.92
    Divorce
    0.90
     Divorce
    0.89
     divor
    0.88
    ArrowToggle
    0.81
    :✨
    0.72
     remar
    0.68
     estranged
    0.66
    Act Density 0.280%

    No Known Activations