INDEX
    Explanations

    mentions of the word "plastic"

    references to plastic and its various forms and implications

    New Auto-Interp
    Negative Logits
     [|
    -0.79
    ---------------
    -0.70
    xual
    -0.69
    FontSize
    -0.69
    xon
    -0.69
    llan
    -0.68
    cffffcc
    -0.68
     4090
    -0.67
    TextColor
    -0.67
     VIDE
    -0.66
    POSITIVE LOGITS
     surgery
    1.02
     filament
    0.97
     bags
    0.95
     Surgery
    0.95
     wrap
    0.95
     tubing
    0.93
     surgeons
    0.93
    ity
    0.92
     surgeon
    0.89
     plastic
    0.89
    Act Density 0.034%

    No Known Activations