Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     of
    -0.94
     so
    -0.91
     in
    -0.91
    ,
    -0.90
     that
    -0.89
     or
    -0.88
    .
    -0.88
     to
    -0.86
     he
    -0.86
     they
    -0.85
    POSITIVE LOGITS
    <bos>
    9.59
    GEBURTSDATUM
    1.89
     ftu
    1.86
    expandindo
    1.81
     ftre
    1.78
     fta
    1.72
    تقاوى
    1.71
     autunno
    1.69
     appunt
    1.66
     betweenstory
    1.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.