INDEX
    Explanations

    terms related to academic degrees, particularly bachelor’s degrees

    New Auto-Interp
    Negative Logits
    abar
    -0.17
     Stem
    -0.15
    ainen
    -0.14
    358
    -0.14
    indre
    -0.14
     Ger
    -0.14
    enden
    -0.14
    ison
    -0.14
    418
    -0.14
    sep
    -0.14
    POSITIVE LOGITS
    hood
    0.27
    arbeit
    0.20
    WidgetItem
    0.19
    lette
    0.19
    -degree
    0.18
    dbg
    0.17
    -pad
    0.17
     наÑĥк
    0.17
    çº
    0.17
    ë²Į
    0.16
    Act Density 0.006%

    No Known Activations