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

    Neuronpedia

    INDEX
    Explanations

    family relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to daughters and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.77
    earch
    -0.71
    ohm
    -0.70
     takedown
    -0.70
    ensus
    -0.66
    NW
    -0.66
    ptions
    -0.65
     Wast
    -0.65
    nergy
    -0.65
     surface
    -0.64
    POSITIVE LOGITS
     aged
    0.97
     nurse
    0.97
     nursing
    0.93
     wheelchair
    0.85
     nurses
    0.85
     whom
    0.83
     grandmother
    0.82
     unmarried
    0.79
     youngest
    0.78
     grandchildren
    0.78
    Act Density 1.195%

    No Known Activations