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

    Neuronpedia

    INDEX
    Explanations

    references to family members and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.79
     للاسماء
    -0.75
    تقاوى
    -0.74
    Lähteet
    -0.71
    脚注の使い方
    -0.70
    InjectAttribute
    -0.66
     enkelte
    -0.65
     vôtre
    -0.63
     financières
    -0.62
    таратура
    -0.62
    POSITIVE LOGITS
     husband
    1.07
     daughter
    1.04
     friend
    0.97
     son
    0.95
     kids
    0.94
     niece
    0.92
     daughters
    0.91
     cousin
    0.88
     nephew
    0.88
     boyfriend
    0.88
    Act Density 0.234%

    No Known Activations