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

    Neuronpedia

    INDEX
    Explanations

    references to family members

    oai_token-act-pair · gpt-3.5-turbo

    mentions of parental figures or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hikers
    -0.71
    intensity
    -0.70
    uve
    -0.66
    owler
    -0.65
    clusions
    -0.63
    IFF
    -0.63
    alist
    -0.62
     tension
    -0.62
    xual
    -0.62
     sqor
    -0.61
    POSITIVE LOGITS
     ancest
    0.83
     died
    0.82
     divorced
    0.82
     uncle
    0.79
    ma
    0.79
     ancestor
    0.76
     ancestors
    0.73
    uncle
    0.73
    hood
    0.72
    husband
    0.72
    Act Density 0.087%

    No Known Activations