INDEX
    Explanations

    references to names, particularly the name "Bern."

    New Auto-Interp
    Negative Logits
    ress
    -0.17
    hee
    -0.16
    ngo
    -0.15
    antry
    -0.15
    nette
    -0.15
    erie
    -0.15
    ilestone
    -0.14
    onnement
    -0.14
    PU
    -0.14
    chestra
    -0.14
    POSITIVE LOGITS
    enville
    0.16
    CRYPT
    0.15
    ROL
    0.14
    eno
    0.14
    ker
    0.14
     popular
    0.14
     contr
    0.14
    ROID
    0.14
    ÏĦÏīν
    0.14
    TRA
    0.14
    Act Density 0.041%

    No Known Activations