INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    IsContent
    -0.78
    LookAnd
    -0.63
     esternos
    -0.60
     Lightboxes
    -0.54
     Exacts
    -0.53
    Demografie
    -0.53
    Expose
    -0.52
    -0.52
     aque
    -0.52
    Preserve
    -0.51
    POSITIVE LOGITS
     go
    0.77
     cross
    0.73
    OrBuilder
    0.60
     come
    0.58
     sleep
    0.58
     jump
    0.58
    stand
    0.57
     stand
    0.57
     sit
    0.55
    cross
    0.54
    Act Density 0.005%

    No Known Activations