INDEX
    Explanations

    names, particularly the name "Rebecca"

    mentions of the name "Rebecca."

    New Auto-Interp
    Negative Logits
    teenth
    -0.95
    pora
    -0.84
    roups
    -0.73
    iatric
    -0.72
    awaru
    -0.70
     dracon
    -0.70
    ician
    -0.69
    ctica
    -0.69
    odynam
    -0.68
    lasses
    -0.68
    POSITIVE LOGITS
    issance
    0.94
     McKenzie
    0.92
     Lopez
    0.86
     Rebecca
    0.82
    anne
    0.79
     Koen
    0.77
     Lowe
    0.75
     Mellon
    0.74
    becca
    0.74
    ãĤ©
    0.73
    Act Density 0.026%

    No Known Activations