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

    Neuronpedia

    INDEX
    Explanations

    array-related operations and code snippets in a programming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aido
    -1.06
    anooga
    -0.81
    grad
    -0.78
    GP
    -0.76
    eur
    -0.75
    hold
    -0.74
    prising
    -0.74
    aeus
    -0.71
    itiz
    -0.71
    cycle
    -0.70
    POSITIVE LOGITS
     args
    0.81
     byte
    0.79
    byte
    0.73
    CHAT
    0.72
    pak
    0.72
    actionDate
    0.71
     ARTICLE
    0.69
    sbm
    0.68
     buf
    0.68
    ilitary
    0.68
    Act Density 0.785%

    No Known Activations