INDEX
    Explanations

    the word "just" in various contexts

    New Auto-Interp
    Negative Logits
    ught
    -0.18
    aub
    -0.18
    alama
    -0.16
    оÑĢоз
    -0.15
    ÃŃž
    -0.15
    craft
    -0.14
    pekt
    -0.14
    bservable
    -0.14
    _compiler
    -0.14
    Spot
    -0.14
    POSITIVE LOGITS
    IFI
    0.17
    ाध
    0.16
     Bor
    0.16
    enger
    0.15
    anda
    0.15
    åѦä¼ļ
    0.15
    aylor
    0.15
    dsl
    0.14
     unpack
    0.14
     Zucker
    0.14
    Act Density 0.030%

    No Known Activations