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

    Neuronpedia

    INDEX
    Explanations

    verbs related to official actions, appointments, and decisions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to government decisions and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.87
    é¾įåĸļ士
    -0.84
    yond
    -0.65
    kr
    -0.64
    wcsstore
    -0.64
    phys
    -0.64
    cum
    -0.63
    yah
    -0.63
    die
    -0.62
    eh
    -0.62
    POSITIVE LOGITS
     him
    0.67
     shotguns
    0.63
     them
    0.62
    ilde
    0.61
     prostitutes
    0.58
     leases
    0.58
     tens
    0.57
    Textures
    0.57
     themselves
    0.57
     copies
    0.57
    Act Density 0.437%

    No Known Activations