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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members or relations

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isexual
    -0.71
    argon
    -0.70
    inen
    -0.69
    pheus
    -0.69
    amina
    -0.68
    arcity
    -0.66
    igo
    -0.65
     guiActiveUn
    -0.64
     Subtle
    -0.63
    uggest
    -0.63
    POSITIVE LOGITS
     members
    1.31
     patriarch
    1.21
    members
    1.12
     reunion
    1.11
     member
    1.10
    member
    0.97
     tree
    0.91
     crest
    0.89
     caregivers
    0.88
     reun
    0.87
    Act Density 0.048%

    No Known Activations