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

    Neuronpedia

    INDEX
    Explanations

    family relationships or family-related events

    oai_token-act-pair · gpt-3.5-turbo

    references to families in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tical
    -0.74
    jriwal
    -0.71
    irection
    -0.70
    ane
    -0.69
    acebook
    -0.69
    imensional
    -0.68
    uart
    -0.67
    lite
    -0.66
    bernatorial
    -0.66
    inen
    -0.66
    POSITIVE LOGITS
     patriarch
    0.98
    members
    0.95
     members
    0.88
     resemb
    0.87
    ILY
    0.86
    member
    0.81
     reunion
    0.81
     crest
    0.80
     resemblance
    0.78
    hood
    0.77
    Act Density 0.035%

    No Known Activations