INDEX
    Explanations

    names of people and places

    New Auto-Interp
    Negative Logits
    ιακ
    -0.15
    uration
    -0.15
    омеÑĢ
    -0.15
    ÑĢеÑģÑĤ
    -0.15
     Bout
    -0.15
    Fox
    -0.15
    çĤī
    -0.14
    rome
    -0.14
    weit
    -0.14
    ing
    -0.14
    POSITIVE LOGITS
    itere
    0.15
    zag
    0.14
    ãĥ«ãĤ¯
    0.14
    ÑĢÑĥк
    0.14
    oley
    0.14
     Lewis
    0.14
    ACHINE
    0.14
    antar
    0.14
    entifier
    0.14
     gift
    0.14
    Act Density 0.034%

    No Known Activations