INDEX
    Explanations

    the conjunction "and" used in various contexts throughout the document

    New Auto-Interp
    Negative Logits
    åIJ¾
    -0.15
     Tal
    -0.14
    gx
    -0.14
    BI
    -0.14
    aģı
    -0.13
    forward
    -0.13
    pler
    -0.13
    gether
    -0.13
    istor
    -0.13
    ॰
    -0.13
    POSITIVE LOGITS
     around
    0.18
    ividual
    0.17
    iggs
    0.16
     off
    0.16
    olland
    0.15
    767
    0.15
     fro
    0.15
     ngoÃłi
    0.14
    ftime
    0.14
    .sam
    0.14
    Act Density 0.016%

    No Known Activations