INDEX
    Explanations

    mentions of the name "Greg."

    New Auto-Interp
    Negative Logits
    xual
    -0.74
    ties
    -0.68
    geon
    -0.67
    LOAD
    -0.67
    making
    -0.65
    lly
    -0.63
    cffffcc
    -0.62
     pregnancies
    -0.62
    clips
    -0.60
    xus
    -0.60
    POSITIVE LOGITS
    arious
    1.41
    orio
    1.34
    orian
    1.32
    orius
    1.28
    ory
    1.20
    ories
    0.98
    orians
    0.95
    orie
    0.95
    ersen
    0.94
    ents
    0.93
    Act Density 0.025%

    No Known Activations