INDEX
    Explanations

    references to class reunions and social connections

    New Auto-Interp
    Negative Logits
    ennon
    -0.14
    argas
    -0.14
    ¢°
    -0.14
    fte
    -0.14
    insky
    -0.14
    lyph
    -0.13
    inci
    -0.13
    пи
    -0.13
    /renderer
    -0.13
    лÑĥг
    -0.13
    POSITIVE LOGITS
     alumni
    0.43
     Alumni
    0.40
     reunion
    0.40
     al
    0.38
     alum
    0.38
     Class
    0.37
     graduates
    0.35
     reun
    0.34
     grads
    0.34
     Grad
    0.31
    Act Density 0.052%

    No Known Activations