INDEX
    Explanations

    flavors and recipes

    New Auto-Interp
    Negative Logits
     flavors
    -1.14
     flavours
    -0.95
     flavor
    -0.86
    flavor
    -0.86
     käns
    -0.79
    RTCK
    -0.73
    StoryboardSegue
    -0.73
     sabores
    -0.71
     Affiliations
    -0.70
     saveurs
    -0.68
    POSITIVE LOGITS
    ing
    0.82
    ed
    0.65
    0.56
     of
    0.50
    ING
    0.50
    ally
    0.49
     that
    0.48
    ably
    0.47
     OF
    0.47
     Allociné
    0.47
    Act Density 0.182%

    No Known Activations