INDEX
    Explanations

    references to waterfalls and water-related imagery

    New Auto-Interp
    Negative Logits
    uhl
    -0.16
    131
    -0.14
    633
    -0.14
    ammer
    -0.14
    _ghost
    -0.14
     Patch
    -0.14
     horizon
    -0.14
    аÑģÑĤи
    -0.13
    636
    -0.13
     handed
    -0.13
    POSITIVE LOGITS
    ityEngine
    0.18
    STE
    0.15
    pane
    0.15
     Sawyer
    0.15
    rops
    0.15
    iform
    0.15
    niÄį
    0.15
     onPage
    0.15
     domestic
    0.14
     dorm
    0.14
    Act Density 0.008%

    No Known Activations