INDEX
    Explanations

    references to popular music acts and their performances

    New Auto-Interp
    Negative Logits
    bart
    -0.15
    -lfs
    -0.15
     Barrel
    -0.14
    .Interop
    -0.14
     Sonata
    -0.13
    ROTO
    -0.13
    AEA
    -0.13
    ChangeEvent
    -0.13
    ACES
    -0.13
    ContentLoaded
    -0.13
    POSITIVE LOGITS
     Spice
    0.34
     spice
    0.28
     Ger
    0.28
     Victoria
    0.24
     ger
    0.22
     Girls
    0.22
     band
    0.22
     Ginger
    0.21
     Simon
    0.21
    Victoria
    0.20
    Act Density 0.008%

    No Known Activations