INDEX
    Explanations

    contrast and opposition

    New Auto-Interp
    Negative Logits
     không
    -1.28
     not
    -1.27
    ไม่
    -1.17
    NotBe
    -1.16
    不仅
    -1.12
    erdings
    -1.12
    Nicht
    -1.12
    genodigd
    -1.09
     zei
    -1.09
    NotBlank
    -1.09
    POSITIVE LOGITS
    而是
    3.31
     nor
    3.06
     instead
    2.69
     Instead
    2.59
     sondern
    2.47
    Instead
    2.41
     but
    2.00
     Nor
    1.95
    Nor
    1.95
    nor
    1.88
    Act Density 0.069%

    No Known Activations