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

    Neuronpedia

    INDEX
    Explanations

    references to family members, especially parents

    oai_token-act-pair · gpt-3.5-turbo

    references to parental figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intensity
    -0.75
    uve
    -0.69
     tension
    -0.69
    abl
    -0.68
    ensitivity
    -0.65
    estyles
    -0.65
    xtap
    -0.65
    Increases
    -0.64
    mble
    -0.63
    awatts
    -0.63
    POSITIVE LOGITS
     uncle
    0.88
     ancestor
    0.86
     eldest
    0.84
    ma
    0.83
    hood
    0.82
     ancest
    0.81
     divorced
    0.81
     ancestors
    0.79
     cousins
    0.79
     grandmother
    0.79
    Act Density 0.073%

    No Known Activations