INDEX
    Explanations

    mentions of the name "Jennifer."

    New Auto-Interp
    Negative Logits
    588
    -0.17
    .tie
    -0.16
    ongo
    -0.15
    illow
    -0.15
    space
    -0.15
    ÑģÑĤав
    -0.14
    vil
    -0.14
    .freeze
    -0.14
     splash
    -0.14
    serrat
    -0.14
    POSITIVE LOGITS
     Lopez
    0.16
    orm
    0.16
    iesel
    0.15
    ifers
    0.15
    iffer
    0.15
     Cool
    0.14
     An
    0.14
    .po
    0.14
    edx
    0.14
     Ps
    0.14
    Act Density 0.005%

    No Known Activations