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

    Neuronpedia

    INDEX
    Explanations

    names and locations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations, names, and specific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unequ
    -0.69
     tails
    -0.60
    gallery
    -0.60
    Indian
    -0.60
    paper
    -0.56
    creen
    -0.56
    ãĢIJ
    -0.55
     toget
    -0.54
    aminer
    -0.54
    Paper
    -0.53
    POSITIVE LOGITS
    isse
    0.76
    illard
    0.73
    ONSORED
    0.71
    uez
    0.71
    ocus
    0.71
     Madness
    0.70
    ibles
    0.69
    arson
    0.69
    ement
    0.68
    uve
    0.67
    Act Density 0.277%

    No Known Activations