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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and siblings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SOUNDBITE
    -0.42
    inWeight
    -0.42
    makeConstraints
    -0.41
    paramref
    -0.39
    heça
    -0.37
    ACHUSET
    -0.36
    المكان
    -0.35
     uVar
    -0.34
    女士
    -0.34
    mappedBy
    -0.34
    POSITIVE LOGITS
     brother
    3.03
     brothers
    2.86
     sister
    2.78
    brother
    2.67
     sibling
    2.64
     Brother
    2.61
     siblings
    2.59
     sisters
    2.56
    Brother
    2.50
     Brothers
    2.45
    Act Density 0.483%

    No Known Activations