INDEX
    Explanations

    articles and determiners in the text

    New Auto-Interp
    Negative Logits
     vorticity
    -0.78
     airfoil
    -0.68
     anthropologist
    -0.68
     archaeologist
    -0.68
     antelope
    -0.66
    <bos>
    -0.66
    Personendaten
    -0.66
     abbot
    -0.65
     epistle
    -0.65
     insec
    -0.65
    POSITIVE LOGITS
     a
    1.61
     an
    1.25
    "):
    
    1.16
     new
    1.07
     large
    1.06
    {}",
    1.06
    '):
    
    1.05
     different
    1.05
    ".
    
    1.02
    ")));
    
    1.02
    Act Density 2.795%

    No Known Activations