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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enforcing rules, mandates, or duties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authority and imposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tribe
    -0.62
     voyage
    -0.58
    beck
    -0.58
     Sioux
    -0.57
     Clyde
    -0.56
     room
    -0.56
    ovies
    -0.56
     Bethlehem
    -0.56
    kers
    -0.56
    adelphia
    -0.55
    POSITIVE LOGITS
    ocide
    0.71
     mantra
    0.71
     stricter
    0.70
    WS
    0.70
    onz
    0.69
     compulsion
    0.68
    rules
    0.68
    azon
    0.67
    bug
    0.67
    atars
    0.67
    Act Density 0.261%

    No Known Activations