INDEX
    Explanations

    mentions of the name "Donald" and associated context, particularly related to political figures and actions

    New Auto-Interp
    Negative Logits
    eden
    -0.17
    lod
    -0.14
    nee
    -0.14
    esub
    -0.14
    eb
    -0.14
    à¤Ĥध
    -0.14
    osed
    -0.14
     getch
    -0.14
    ̣
    -0.14
    ebb
    -0.13
    POSITIVE LOGITS
    828
    0.15
    RunWith
    0.14
    pres
    0.14
     bil
    0.14
    irl
    0.14
    alin
    0.14
    -sama
    0.14
    aghan
    0.14
    wich
    0.13
    abeth
    0.13
    Act Density 0.021%

    No Known Activations