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

    Neuronpedia

    INDEX
    Explanations

    references to families and specific family members

    oai_token-act-pair · gpt-3.5-turbo

    references to family members and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isexual
    -0.71
    acebook
    -0.71
    xual
    -0.67
    jriwal
    -0.66
    igo
    -0.65
    psey
    -0.65
    uggest
    -0.64
    tical
    -0.64
     Subtle
    -0.64
    ipolar
    -0.63
    POSITIVE LOGITS
     patriarch
    1.08
     crest
    0.93
     members
    0.89
    members
    0.87
     tree
    0.81
    member
    0.80
     belongings
    0.79
     heirs
    0.77
     reunion
    0.76
     pets
    0.71
    Act Density 0.060%

    No Known Activations