INDEX
    Explanations

    mentions of specific individuals, political terms, and related keywords

    New Auto-Interp
    Negative Logits
    Ł
    -0.15
     pel
    -0.15
    _rwlock
    -0.15
    айÑĤ
    -0.15
     passing
    -0.15
     Pel
    -0.15
     Dak
    -0.14
     pass
    -0.14
    ushima
    -0.14
    cke
    -0.14
    POSITIVE LOGITS
     Mes
    0.16
    istrat
    0.16
    finger
    0.16
    MLE
    0.16
    istance
    0.15
    UiThread
    0.15
    esa
    0.15
    Mes
    0.15
    ũi
    0.15
    Ïĩο
    0.15
    Act Density 0.030%

    No Known Activations