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

    Neuronpedia

    INDEX
    Explanations

    features or rules mentioned in technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of features and rules in technology contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amples
    -0.91
    TeX
    -0.83
     largeDownload
    -0.76
    endars
    -0.75
    eeds
    -0.70
    ockets
    -0.68
    aples
    -0.65
    IGHTS
    -0.63
    llah
    -0.63
    orters
    -0.63
    POSITIVE LOGITS
     whereby
    0.75
     nicknamed
    0.72
     applied
    0.71
     called
    0.69
     applies
    0.67
    uses
    0.67
     loophole
    0.66
     known
    0.66
     workaround
    0.66
     MGM
    0.65
    Act Density 0.316%

    No Known Activations