INDEX
    Explanations

    references to specific political events and figures

    New Auto-Interp
    Negative Logits
    rganization
    -0.19
    mbH
    -0.15
    iltr
    -0.15
    ìĿ´ë¹Ħ
    -0.15
    uelle
    -0.14
    cÃŃ
    -0.14
     Swinger
    -0.14
    aille
    -0.14
    udiant
    -0.14
    ÙĪØ³ÛĮ
    -0.14
    POSITIVE LOGITS
    eder
    0.15
    erk
    0.15
     nine
    0.14
    wid
    0.14
    argo
    0.14
     
    0.14
    isse
    0.14
    eree
    0.14
    ear
    0.13
    243
    0.13
    Act Density 0.181%

    No Known Activations