INDEX
    Explanations

    content related to literature and literary works

    New Auto-Interp
    Negative Logits
    ery
    -0.19
    ors
    -0.18
    ement
    -0.17
    ers
    -0.16
    asma
    -0.16
    heit
    -0.16
    ster
    -0.16
    گاÙĩ
    -0.16
    ing
    -0.15
    ÑĪи
    -0.15
    POSITIVE LOGITS
    /art
    0.22
    /movie
    0.17
    /language
    0.17
    /video
    0.17
    igon
    0.17
     Yön
    0.17
    /media
    0.16
    íĭ±
    0.16
    ÑĤÑİ
    0.16
    ervo
    0.16
    Act Density 0.029%

    No Known Activations