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

    Neuronpedia

    INDEX
    Explanations

    URL sources in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of source code references or source file paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.87
    osate
    -0.75
     mosqu
    -0.74
    theless
    -0.73
     lapse
    -0.69
    pherd
    -0.68
    secut
    -0.67
    phis
    -0.66
    ocene
    -0.65
    etheless
    -0.65
    POSITIVE LOGITS
     src
    0.98
    src
    0.94
    Path
    0.81
     dst
    0.80
    ="/
    0.80
    natureconservancy
    0.79
    Loader
    0.78
    hack
    0.77
    cms
    0.77
    ãĥĥãĥī
    0.74
    Act Density 0.012%

    No Known Activations