INDEX
    Explanations

    quotations and song titles

    New Auto-Interp
    Negative Logits
    sth
    -0.15
     revolution
    -0.15
     Toll
    -0.14
    zu
    -0.14
    inq
    -0.14
    ound
    -0.14
    .SelectCommand
    -0.14
    vek
    -0.14
    imate
    -0.13
    adio
    -0.13
    POSITIVE LOGITS
    nem
    0.16
    (Spring
    0.16
     Bei
    0.15
     Minority
    0.14
    linger
    0.14
     Lover
    0.14
    orgen
    0.14
    Bei
    0.14
    Laura
    0.14
    arin
    0.14
    Act Density 0.005%

    No Known Activations