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

    Neuronpedia

    INDEX
    Explanations

    names related to artists and individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with notable last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.78
    catentry
    -0.71
    -+-+
    -0.69
     Adin
    -0.69
    RET
    -0.65
    ģĸ
    -0.64
     Citiz
    -0.64
     Drift
    -0.61
     Crunch
    -0.60
     territorial
    -0.60
    POSITIVE LOGITS
    hof
    1.03
    acht
    0.75
    opol
    0.72
    ocent
    0.70
    ophon
    0.70
    nikov
    0.70
    utical
    0.68
    geist
    0.68
    asin
    0.66
    iency
    0.66
    Act Density 0.093%

    No Known Activations