INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     divisions
    -0.08
    -0.08
    BR
    -0.08
    look
    -0.08
    iew
    -0.08
    orea
    -0.07
     BR
    -0.07
    inese
    -0.07
     Fri
    -0.07
    looks
    -0.07
    POSITIVE LOGITS
     umbrella
    0.08
     Chamber
    0.07
    _ACT
    0.07
     Attached
    0.07
     detained
    0.07
     detention
    0.07
     Invit
    0.07
    _CONF
    0.07
    	stmt
    0.07
    .JSONException
    0.07
    Act Density 0.002%

    No Known Activations