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

    Neuronpedia

    INDEX
    Explanations

    references to family structures and dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of children in family contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioxide
    -0.73
    tten
    -0.67
    PORT
    -0.66
     militar
    -0.65
     Lank
    -0.62
     crude
    -0.61
     Reich
    -0.61
     Cowboy
    -0.61
    pmwiki
    -0.59
     freight
    -0.59
    POSITIVE LOGITS
    riages
    0.94
    arten
    0.88
    children
    0.84
     orphans
    0.83
     inherit
    0.83
     grandchildren
    0.83
    mares
    0.82
    parents
    0.78
    daughter
    0.77
    thood
    0.76
    Act Density 0.086%

    No Known Activations