INDEX
    Explanations

    mentions of the name "Justin" in various contexts

    New Auto-Interp
    Negative Logits
     ucwords
    -0.17
    gne
    -0.16
     dis
    -0.15
    ylum
    -0.15
    abus
    -0.14
    hole
    -0.14
    IED
    -0.14
    ishly
    -0.14
     actionTypes
    -0.14
    UES
    -0.14
    POSITIVE LOGITS
     Bieber
    0.32
    iano
    0.25
    ian
    0.25
     Trudeau
    0.25
     Timber
    0.22
    IAN
    0.20
    ians
    0.19
    iana
    0.19
    ifiable
    0.18
    iane
    0.18
    Act Density 0.003%

    No Known Activations