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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Daughter
    -0.24
     daughter
    -0.18
     Wife
    -0.17
     granddaughter
    -0.16
    daughter
    -0.16
     Sons
    -0.16
    wife
    -0.15
    妻
    -0.15
     Heller
    -0.15
     wife
    -0.15
    POSITIVE LOGITS
    Unc
    0.61
     uncle
    0.60
    unc
    0.60
     Unc
    0.57
     Uncle
    0.56
     aunt
    0.52
    _unc
    0.52
     Aunt
    0.47
    UNC
    0.44
     relative
    0.43
    Act Density 0.329%

    No Known Activations