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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rex
    -0.07
     recommended
    -0.07
    _import
    -0.07
    乙烯
    -0.07
    Uno
    -0.06
     ();↵
    -0.06
     mot
    -0.06
    展厅
    -0.06
     summarized
    -0.06
    dis
    -0.06
    POSITIVE LOGITS
     этот
    0.08
    .sha
    0.07
    .symbol
    0.07
    EQUAL
    0.07
    POINT
    0.07
     trilogy
    0.07
    /modal
    0.07
     проц
    0.07
     acab
    0.07
    )>
    0.06
    Act Density 0.001%

    No Known Activations