INDEX
    Explanations

    specific references to iconic music and film works

    New Auto-Interp
    Negative Logits
     newest
    -0.18
     new
    -0.17
     latest
    -0.17
    atten
    -0.16
    latest
    -0.15
    romise
    -0.15
    ä»ĭ
    -0.14
    Reporter
    -0.14
     promising
    -0.14
    å±ĭ
    -0.14
    POSITIVE LOGITS
     classics
    0.25
     classic
    0.23
     underrated
    0.22
     seminal
    0.21
     masterpiece
    0.21
     canonical
    0.19
    canonical
    0.18
     proto
    0.18
     landmark
    0.18
    classic
    0.18
    Act Density 0.222%

    No Known Activations