INDEX
    Explanations

    references to historical narratives and reinterpretations of race relations

    New Auto-Interp
    Negative Logits
     occaf
    -0.47
    姿
    -0.44
    جمعیت
    -0.44
     Chriftian
    -0.44
     muri
    -0.44
     confider
    -0.43
     someone
    -0.43
    новременно
    -0.42
     miſ
    -0.42
     neceſſ
    -0.42
    POSITIVE LOGITS
    httphttps
    0.99
     Италијани
    0.81
     nakalista
    0.80
    MLLoader
    0.79
    ArrowToggle
    0.79
    󠁢
    0.77
    ‚¬
    0.76
     herein
    0.73
    featureID
    0.71
    ValueStyle
    0.69
    Act Density 0.228%

    No Known Activations