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

    Neuronpedia

    INDEX
    Explanations

    mentions of friends and family in conversational contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention relationships with family and friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oliberal
    -0.77
    arbon
    -0.69
    */(
    -0.69
    ãĥķãĤ©
    -0.66
    onet
    -0.62
    ï¸
    -0.62
     Canaver
    -0.61
     gears
    -0.60
    umph
    -0.59
     pollut
    -0.58
    POSITIVE LOGITS
     coworkers
    0.87
     sibling
    0.83
    mates
    0.83
     acquaintances
    0.83
     neighbors
    0.83
     siblings
    0.82
     neighbours
    0.81
     strangers
    0.78
     relatives
    0.76
    friends
    0.74
    Act Density 0.313%

    No Known Activations