INDEX
    Explanations

    words related to preparation or preparation-related actions

    references to preparation

    New Auto-Interp
    Negative Logits
     Bur
    -0.66
    sil
    -0.65
     peacefully
    -0.63
    itar
    -0.62
    taboola
    -0.61
     Viol
    -0.61
     Hor
    -0.61
    Image
    -0.61
    cious
    -0.61
    angered
    -0.60
    POSITIVE LOGITS
     prep
    4.07
    prep
    2.51
     Prep
    1.93
    Prep
    1.63
     preparation
    1.36
     prepar
    1.30
     Prepar
    1.20
     prec
    1.05
     pre
    1.01
     prepare
    0.98
    Act Density 0.015%

    No Known Activations