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

    Neuronpedia

    INDEX
    Explanations

    references to arrays in a programming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    doms
    -0.69
    jured
    -0.69
    phrine
    -0.67
    é¾įå¥ij士
    -0.66
    mins
    -0.65
    conom
    -0.65
    days
    -0.63
     Mart
    -0.62
    mitt
    -0.61
    wolves
    -0.61
    POSITIVE LOGITS
     subscript
    1.06
     array
    0.88
     consisting
    0.86
     comprised
    0.86
     comprising
    0.85
    Buffer
    0.82
     composed
    0.75
    arium
    0.74
     encomp
    0.74
    mble
    0.73
    Act Density 0.042%

    No Known Activations