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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    specific user mentions and interactive elements in online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Perez
    -0.82
     Gins
    -0.82
     GP
    -0.81
     Franco
    -0.80
     Hasan
    -0.80
     Cole
    -0.79
     Gian
    -0.78
     Lei
    -0.77
     Fein
    -0.76
     Ryan
    -0.76
    POSITIVE LOGITS
    arn
    0.94
    ¥µ
    0.91
    AV
    0.89
    ya
    0.86
    Ĵ
    0.85
    chanted
    0.83
    av
    0.83
     AV
    0.83
    BOX
    0.82
     Vessel
    0.81
    Act Density 0.366%

    No Known Activations