INDEX
    Explanations

    occurrences of sunsets and related imagery or themes

    New Auto-Interp
    Negative Logits
    erged
    -0.15
    allel
    -0.15
    каÑģ
    -0.14
    annis
    -0.14
    vely
    -0.14
     adel
    -0.14
    annes
    -0.14
    ÄĽn
    -0.13
    íĮ
    -0.13
    ijIJ
    -0.13
    POSITIVE LOGITS
    ropp
    0.17
     borderTop
    0.15
     Král
    0.15
    iParam
    0.15
    akis
    0.15
    uggle
    0.15
    hone
    0.15
    #
    0.15
     Huffman
    0.14
    ichten
    0.14
    Act Density 0.041%

    No Known Activations