INDEX
    Explanations

    references to boats

    New Auto-Interp
    Negative Logits
    arial
    -0.77
    naires
    -0.69
    eyes
    -0.65
    heimer
    -0.64
    abilia
    -0.63
    ENCE
    -0.62
     Lamar
    -0.61
    Reviewed
    -0.61
    aneous
    -0.61
     Staples
    -0.61
    POSITIVE LOGITS
    boat
    1.26
    wright
    1.17
    loads
    1.17
    boats
    1.11
    load
    1.04
     docks
    1.01
     Graveyard
    0.98
    wreck
    0.98
     dock
    0.96
     captain
    0.96
    Act Density 0.032%

    No Known Activations