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

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual or political figure named Harper

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to the name "Harper."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mble
    -0.89
    olean
    -0.86
    etermination
    -0.82
    ership
    -0.81
    angular
    -0.80
    eanor
    -0.79
    uctor
    -0.79
    urtle
    -0.79
    sembly
    -0.79
    atility
    -0.78
    POSITIVE LOGITS
    Collins
    1.19
     Harper
    0.90
     Trudeau
    0.77
    DOM
    0.74
    weather
    0.72
    shire
    0.71
    stein
    0.69
    Teen
    0.68
     penn
    0.68
    pin
    0.65
    Act Density 0.012%

    No Known Activations