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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     successfully
    -0.32
     extra
    -0.32
    ky
    -0.30
     Sat
    -0.30
     for
    -0.30
     term
    -0.30
     relative
    -0.30
     split
    -0.29
     range
    -0.29
     be
    -0.29
    POSITIVE LOGITS
    ofs
    0.31
    ickness
    0.29
    hibited
    0.28
    iku
    0.28
    -dollar
    0.28
    -expanded
    0.27
    anko
    0.27
    ä¸įè¶ħè¿ĩ
    0.27
    hibit
    0.27
    igg
    0.26
    Act Density 0.012%

    No Known Activations

    This feature has no known activations.