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

    Neuronpedia

    INDEX
    Explanations

    references to static data or concepts related to static properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    /*-
    -0.65
    urlopen
    -0.64
     Yeh
    -0.63
     habitudes
    -0.63
    مره
    -0.63
    Yeh
    -0.62
    blum
    -0.62
    تیب
    -0.60
    Agosto
    -0.59
    cault
    -0.59
    POSITIVE LOGITS
    twimg
    0.88
    Statics
    0.70
     متعلقه
    0.69
     Static
    0.66
     surla
    0.65
     terça
    0.64
    Static
    0.62
     Mathieu
    0.62
    fjspx
    0.62
    脚注の使い方
    0.61
    Act Density 0.006%

    No Known Activations