INDEX
    Explanations

    mentions of the name "Jennifer."

    New Auto-Interp
    Negative Logits
    illow
    -0.18
    .tie
    -0.16
    .scalablytyped
    -0.15
    ffective
    -0.15
    usz
    -0.15
     erotische
    -0.14
    .freeze
    -0.14
    GING
    -0.14
    ongo
    -0.14
    cü
    -0.14
    POSITIVE LOGITS
    iar
    0.15
     Lopez
    0.15
    .po
    0.14
    orm
    0.14
    isation
    0.14
    ulk
    0.14
    bet
    0.13
    ya
    0.13
     Dawn
    0.13
    ization
    0.13
    Act Density 0.003%

    No Known Activations