INDEX
    Explanations

    references to punk culture and themes

    New Auto-Interp
    Negative Logits
    desk
    -0.18
    ought
    -0.16
    anh
    -0.15
    ippers
    -0.15
    onest
    -0.15
    \Array
    -0.15
    alis
    -0.15
    esan
    -0.14
    -await
    -0.14
    imens
    -0.14
    POSITIVE LOGITS
     dil
    0.17
    ìłķìĿĦ
    0.15
    elli
    0.15
     Prem
    0.14
    žel
    0.14
    NSSet
    0.14
     Baba
    0.14
    IPC
    0.14
    rung
    0.14
     Nicolas
    0.14
    Act Density 0.004%

    No Known Activations