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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence and competence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unknownFields
    -0.47
     their
    -0.36
     its
    -0.35
    <bos>
    -0.34
     album
    -0.33
     few
    -0.33
    getPost
    -0.33
    Section
    -0.33
     estre
    -0.32
     Pullman
    -0.32
    POSITIVE LOGITS
     Smart
    0.88
    Intelligent
    0.84
    Smart
    0.84
     Intelligent
    0.83
     Intelligence
    0.82
     smartest
    0.81
    smart
    0.80
    Wise
    0.79
     SMART
    0.79
    intelligent
    0.79
    Act Density 0.229%

    No Known Activations