INDEX
    Explanations

    mentions of arts and cultural topics

    New Auto-Interp
    Negative Logits
    achi
    -0.15
    кеÑĤ
    -0.15
    aty
    -0.15
    UGIN
    -0.14
     Candle
    -0.14
    HONE
    -0.14
    aku
    -0.14
    éĴŁ
    -0.14
     Pty
    -0.14
    _topic
    -0.13
    POSITIVE LOGITS
     arts
    0.30
     Arts
    0.28
     Cultural
    0.24
     cultural
    0.24
     museums
    0.21
     museum
    0.21
     culture
    0.20
     Culture
    0.20
     Muse
    0.19
    -cultural
    0.19
    Act Density 0.179%

    No Known Activations