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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical procedures or operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to specific actions occurring at particular times or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phabet
    -0.79
    DonaldTrump
    -0.75
     altogether
    -0.75
    à¥
    -0.68
     enjoyed
    -0.67
     eaten
    -0.67
     gladly
    -0.67
     thereof
    -0.66
    izens
    -0.66
    @@@@@@@@
    -0.65
    POSITIVE LOGITS
    tnc
    0.87
     labs
    0.81
     laboratories
    0.79
     ponds
    0.75
     Brisbane
    0.73
     Leopard
    0.73
     laboratory
    0.73
    raq
    0.71
     Laboratory
    0.70
     outskirts
    0.69
    Act Density 0.463%

    No Known Activations