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

    Neuronpedia

    INDEX
    Explanations

    phrases related to connections between family and friends

    oai_token-act-pair · gpt-3.5-turbo

    references to family and friends in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _(
    -0.72
     WRITE
    -0.67
    fail
    -0.66
     TYPE
    -0.63
     Module
    -0.62
    lamm
    -0.60
    Layer
    -0.60
    ãĥĢ
    -0.60
    recomm
    -0.59
    iencies
    -0.59
    POSITIVE LOGITS
     friends
    1.64
     neighbours
    1.35
     neighbors
    1.35
     siblings
    1.31
     acquaintances
    1.30
     grandparents
    1.29
    friends
    1.28
     grandchildren
    1.25
     coworkers
    1.24
     friendships
    1.20
    Act Density 0.116%

    No Known Activations