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

    Neuronpedia

    INDEX
    Explanations

    mentions of possession or personal ownership

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to individuality and personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cery
    -0.71
    actionDate
    -0.71
    boa
    -0.66
    trap
    -0.66
     RHP
    -0.63
    uve
    -0.63
    assium
    -0.62
    both
    -0.62
    arnaev
    -0.62
     SPR
    -0.61
    POSITIVE LOGITS
     struggles
    0.71
    isms
    0.69
     selves
    0.69
    izations
    0.69
     styles
    0.67
     ventures
    0.64
     pursuits
    0.63
    isations
    0.62
     prejudices
    0.61
     demons
    0.61
    Act Density 0.172%

    No Known Activations