INDEX
    Explanations

    expressions indicating possession or ownership

    New Auto-Interp
    Negative Logits
    .?
    -0.83
    .",
    -0.77
    ?",
    -0.70
    â̦."
    -0.68
    â̦..
    -0.67
    estine
    -0.67
    .....
    -0.65
    .,"
    -0.63
    .;
    -0.61
    â̦.
    -0.61
    POSITIVE LOGITS
    ãĥ¥
    0.65
    ãĥĩãĤ£
    0.60
     nod
    0.60
     unwitting
    0.59
     nods
    0.59
     bits
    0.57
     winds
    0.57
     cue
    0.56
     hefty
    0.56
    itudinal
    0.55
    Act Density 0.377%

    No Known Activations