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

    Neuronpedia

    INDEX
    Explanations

    high-dimensional vectors

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematical or computational vectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.88
    soDeliveryDate
    -0.78
    rontal
    -0.75
    noxious
    -0.73
    areth
    -0.73
    lished
    -0.72
    ptions
    -0.71
    ulhu
    -0.71
    kens
    -0.70
    earance
    -0.70
    POSITIVE LOGITS
     Vector
    0.97
    vector
    0.85
     vector
    0.85
    icles
    0.81
    istani
    0.79
    icular
    0.77
    idian
    0.75
     representations
    0.73
     vectors
    0.73
    ization
    0.71
    Act Density 0.019%

    No Known Activations