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

    Neuronpedia

    INDEX
    Explanations

    references to family members, particularly siblings

    oai_token-act-pair · gpt-3.5-turbo

    references to siblings and twin relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cens
    -0.72
    ventory
    -0.71
     Talks
    -0.68
    nesty
    -0.68
    hops
    -0.67
    rays
    -0.67
     Bots
    -0.66
    Numbers
    -0.65
     amnesty
    -0.64
    robe
    -0.64
    POSITIVE LOGITS
     sibling
    2.38
     twin
    2.17
     siblings
    1.87
     Twin
    1.26
    iblings
    1.09
    ibling
    0.99
     sister
    0.99
     brother
    0.98
     cousins
    0.92
     cousin
    0.91
    Act Density 0.011%

    No Known Activations