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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ownership or specific attribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize personal rights and autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cery
    -0.69
    aundering
    -0.67
    uve
    -0.66
    ulic
    -0.66
    amba
    -0.66
    actionDate
    -0.66
    duct
    -0.65
    lav
    -0.65
    cott
    -0.64
    ashtra
    -0.63
    POSITIVE LOGITS
    imei
    0.70
     selves
    0.66
     struggles
    0.64
    isms
    0.63
     styles
    0.63
     ventures
    0.62
     creations
    0.62
    isations
    0.60
     quirks
    0.60
     traditions
    0.59
    Act Density 0.161%

    No Known Activations