INDEX
    Explanations

    mentions of "fellow" or similar terms indicating community or camaraderie

    New Auto-Interp
    Negative Logits
    parentId
    -0.60
    mauer
    -0.59
     masculina
    -0.59
     Eras
    -0.58
    ricanes
    -0.57
     Silt
    -0.57
    ldorf
    -0.57
     harapan
    -0.57
     caprice
    -0.56
    mazaki
    -0.56
    POSITIVE LOGITS
     fellow
    3.40
    Fellow
    3.16
     Fellow
    3.10
     FELLOW
    2.90
    fellow
    2.88
     fellows
    2.23
     Fellows
    2.18
     Fellowship
    1.68
     fellowship
    1.57
     Fellowships
    1.43
    Act Density 0.049%

    No Known Activations