INDEX
    Explanations

    references to artistic critique or analysis

    New Auto-Interp
    Negative Logits
     клÑĥ
    -0.15
    furt
    -0.14
    hiro
    -0.14
     ÑĢанÑĮ
    -0.14
    arts
    -0.14
    áv
    -0.13
    opsis
    -0.13
    ContextHolder
    -0.13
    469
    -0.13
    alam
    -0.13
    POSITIVE LOGITS
     Ros
    0.21
     pa
    0.21
     Uk
    0.20
     lud
    0.19
    Ros
    0.19
     sowie
    0.18
     Jug
    0.17
     pol
    0.17
     bols
    0.16
     Ni
    0.16
    Act Density 0.054%

    No Known Activations