INDEX
    Explanations

    the word "it" and the contraction "it's"

    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.75
     Browne
    -0.59
     itself
    -0.58
    canestro
    -0.58
    -0.57
    setVerticalGroup
    -0.55
     Schumer
    -0.54
    obs
    -0.53
    ویش
    -0.53
     features
    -0.52
    POSITIVE LOGITS
     Савезне
    0.84
     متعلقه
    0.80
     Efq
    0.75
     $_"
    0.68
    Glit
    0.67
     myſelf
    0.67
    */;
    0.65
    there
    0.63
     Jefus
    0.62
     Ut
    0.62
    Act Density 0.120%

    No Known Activations