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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating influence or control over others

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their interactions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertising
    -0.79
     Cosponsors
    -0.71
    \/\/
    -0.70
    ben
    -0.69
     coward
    -0.68
    GEN
    -0.68
    ¥µ
    -0.63
     Lauder
    -0.62
    haps
    -0.62
    iple
    -0.62
    POSITIVE LOGITS
     pegged
    0.86
     nailed
    0.86
     installed
    0.85
     figured
    0.81
     hooked
    0.79
     towed
    0.78
     implanted
    0.77
     sorted
    0.75
     authenticated
    0.73
    icum
    0.73
    Act Density 0.397%

    No Known Activations