INDEX
    Explanations

    mentions of the name "Maurice" with a particularly high activation for the name "Maurice" itself

    references to specific individuals or places, particularly the name "Maurice" and associated terms

    New Auto-Interp
    Negative Logits
     pend
    -0.82
    apsed
    -0.76
     extrem
    -0.74
     pope
    -0.74
    iger
    -0.72
    inez
    -0.70
     occup
    -0.68
    assed
    -0.68
     batters
    -0.67
    omez
    -0.67
    POSITIVE LOGITS
    flake
    0.97
    tp
    0.90
    dra
    0.88
    mallow
    0.88
    fw
    0.85
    twitter
    0.80
    intosh
    0.78
    dust
    0.77
    Berry
    0.77
    berry
    0.77
    Act Density 0.022%

    No Known Activations