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

    Neuronpedia

    INDEX
    Explanations

    multiple occurrences of commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     which
    -0.45
     who
    -0.45
     SIMBAD
    -0.44
    ługa
    -0.44
    Herkunft
    -0.44
     whose
    -0.43
    dinga
    -0.43
     and
    -0.41
     chirurg
    -0.41
    évaluateur
    -0.41
    POSITIVE LOGITS
    )");
    0.79
     فريبيس
    0.77
     AssemblyCompany
    0.76
    )";
    0.75
    WebServlet
    0.74
     autorytatywna
    0.74
    \{\\
    0.70
     "");
    0.69
    المناصب
    0.69
    *}
    0.68
    Act Density 0.010%

    No Known Activations