INDEX
    Explanations

    occurrences of the name "George."

    New Auto-Interp
    Negative Logits
    nn
    -0.17
    tsky
    -0.16
    ition
    -0.16
    raž
    -0.15
    itia
    -0.15
    posables
    -0.15
    ogue
    -0.15
    dep
    -0.15
    ücken
    -0.15
    éĥİ
    -0.15
    POSITIVE LOGITS
    ople
    0.14
     Anatomy
    0.14
    opers
    0.14
    aint
    0.14
    asl
    0.13
    stalk
    0.13
    ville
    0.13
     Literature
    0.13
    ully
    0.13
    ertz
    0.13
    Act Density 0.018%

    No Known Activations