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

    Neuronpedia

    INDEX
    Explanations

    statements that quantify or compare groups, particularly in discussions around race or social issues

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.94
     مشين
    -0.91
     createState
    -0.87
    JspWriter
    -0.84
     ―――――
    -0.77
    withIdentifier
    -0.77
    цездатний
    -0.76
    клопе
    -0.76
     doInBackground
    -0.76
     мәкал
    -0.74
    POSITIVE LOGITS
    COL
    0.59
    addContainerGap
    0.55
    kha
    0.53
     ra
    0.51
     Col
    0.50
     COL
    0.47
     ./
    0.47
     fortunately
    0.47
     col
    0.47
    辞典
    0.46
    Act Density 0.008%

    No Known Activations