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

    Neuronpedia

    INDEX
    Explanations

    warnings or prohibitive language in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "):
    -0.77
    __":
    -0.74
    itemBuilder
    -0.74
    WebServlet
    -0.72
    "],
    -0.71
    "),
    -0.71
    "){
    -0.70
    ")){
    -0.69
     """
    -0.69
    zarchiwizowane
    -0.68
    POSITIVE LOGITS
    !
    0.76
    !!!
    0.65
    !!
    0.60
    !!!!
    0.57
    !.
    0.57
    ;
    0.56
    ー
    0.55
    Билгалдахарш
    0.55
     poveznice
    0.54
    !!!!!
    0.53
    Act Density 0.895%

    No Known Activations