INDEX
    Explanations

    occurrences of the word "has" and its variations

    New Auto-Interp
    Negative Logits
    took
    -0.18
     Came
    -0.18
    came
    -0.18
    went
    -0.17
     saw
    -0.17
     threw
    -0.16
    was
    -0.15
     gave
    -0.15
     underwent
    -0.15
     came
    -0.15
    POSITIVE LOGITS
     been
    0.40
    htag
    0.34
    htags
    0.30
     Been
    0.30
    been
    0.29
     BEEN
    0.28
     become
    0.26
    Been
    0.24
     sido
    0.24
    nt
    0.23
    Act Density 0.071%

    No Known Activations