INDEX
    Explanations

    words expressing affection or nostalgia

    New Auto-Interp
    Negative Logits
    allon
    -0.17
    itect
    -0.15
    936
    -0.15
    ccione
    -0.14
    ctic
    -0.14
    ender
    -0.14
     bằng
    -0.14
    dna
    -0.14
     Kingdom
    -0.14
    DNA
    -0.14
    POSITIVE LOGITS
    kee
    0.15
    laus
    0.15
    imes
    0.15
    親
    0.15
    ÑģÑĥÑĤ
    0.15
    rosse
    0.14
    лÑıв
    0.14
    imers
    0.14
    nut
    0.13
    wyn
    0.13
    Act Density 0.004%

    No Known Activations