INDEX
    Explanations

    commemorates dedications tributes

    New Auto-Interp
    Negative Logits
     ceremonial
    -0.11
     elabor
    -0.11
     Hindered
    -0.10
     congrat
    -0.10
     unfavor
    -0.09
     Masc
    -0.09
    ardy
    -0.09
    åĸĦ
    -0.09
     Femme
    -0.08
     Karma
    -0.08
    POSITIVE LOGITS
     memory
    0.30
     dedicated
    0.28
     ÑĩеÑģÑĤÑĮ
    0.27
    纪
    0.25
     tribute
    0.25
     trib
    0.24
    ded
    0.23
     dedication
    0.23
     Memory
    0.22
    tribute
    0.22
    Act Density 0.155%

    No Known Activations