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

    Neuronpedia

    INDEX
    Explanations

    high-dimensional mathematical vectors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to high-dimensional vectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.84
    soDeliveryDate
    -0.81
    ecause
    -0.75
    earance
    -0.72
    perty
    -0.71
    razen
    -0.70
    cffffcc
    -0.69
    noxious
    -0.69
    rontal
    -0.69
    areth
    -0.68
    POSITIVE LOGITS
     Vector
    0.92
     vector
    0.92
    vector
    0.89
     vectors
    0.81
    Ñĭ
    0.80
    icles
    0.79
    icular
    0.78
    istani
    0.77
    и
    0.71
    idian
    0.71
    Act Density 0.009%

    No Known Activations