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

    Neuronpedia

    INDEX
    Explanations

    image source URLs

    oai_token-act-pair · gpt-3.5-turbo

    source code and related components in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.86
    theless
    -0.77
     lapse
    -0.75
    stood
    -0.72
    pherd
    -0.71
    phis
    -0.69
    awaru
    -0.68
    wagen
    -0.67
    ocene
    -0.66
    osate
    -0.66
    POSITIVE LOGITS
     src
    0.95
    src
    0.94
    ="/
    0.91
    natureconservancy
    0.82
    english
    0.81
    cms
    0.80
     dst
    0.80
    hack
    0.78
    Path
    0.77
    ="#
    0.75
    Act Density 0.011%

    No Known Activations