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

    Neuronpedia

    INDEX
    Explanations

    words related to exerting influence or power

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.75
    TAG
    -0.73
    leigh
    -0.69
    uberty
    -0.67
    cise
    -0.67
    ns
    -0.66
    onew
    -0.66
    ITIES
    -0.65
    Quotes
    -0.65
    MQ
    -0.65
    POSITIVE LOGITS
     pedd
    1.10
     cooker
    0.94
     exerted
    0.87
     influence
    0.81
     influencing
    0.78
     multiplier
    0.77
     sway
    0.76
     pupp
    0.76
    orship
    0.75
    ability
    0.74
    Act Density 0.038%

    No Known Activations