INDEX
    Explanations

    conjunctions and their surrounding context in sentences

    New Auto-Interp
    Negative Logits
    ViewInit
    -0.15
     Pitch
    -0.15
    ä¼Ļ
    -0.15
    alama
    -0.14
     tut
    -0.14
     Turnbull
    -0.14
    Pitch
    -0.14
    anes
    -0.14
    bial
    -0.14
     pitches
    -0.14
    POSITIVE LOGITS
    AGR
    0.16
    pees
    0.15
    лика
    0.14
    yy
    0.14
    skins
    0.14
    OLOR
    0.14
    мена
    0.14
    rew
    0.14
    midd
    0.13
     Sands
    0.13
    Act Density 0.142%

    No Known Activations