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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uve
    -0.75
    intensity
    -0.74
    estyles
    -0.69
    abl
    -0.67
     tension
    -0.67
    xtap
    -0.66
    spir
    -0.64
    Increases
    -0.64
     hikers
    -0.63
     staffing
    -0.62
    POSITIVE LOGITS
     uncle
    0.92
     ancestor
    0.86
     eldest
    0.84
     divorced
    0.84
     ancest
    0.83
    ma
    0.82
     ancestors
    0.81
     patriarch
    0.80
     died
    0.79
    uncle
    0.79
    Act Density 0.065%

    No Known Activations