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

    Neuronpedia

    INDEX
    Explanations

    keywords related to historical events or backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    references to historical context or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jab
    -0.82
    nets
    -0.81
    */(
    -0.78
    pload
    -0.75
    emouth
    -0.73
    fman
    -0.71
    rat
    -0.70
    atum
    -0.69
    alties
    -0.66
    asking
    -0.66
    POSITIVE LOGITS
     mankind
    0.81
     warfare
    0.78
     Invention
    0.75
     humankind
    0.75
     Pione
    0.73
     heroism
    0.72
     Warfare
    0.68
     hostilities
    0.68
     thous
    0.67
     colonialism
    0.67
    Act Density 0.108%

    No Known Activations