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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and parental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (completion
    -0.17
     buddy
    -0.16
    edia
    -0.15
    äºĮ人
    -0.15
    ollipop
    -0.15
     μη
    -0.15
    -valu
    -0.15
     dikke
    -0.14
    gii
    -0.14
    )throws
    -0.14
    POSITIVE LOGITS
     sons
    0.40
     children
    0.37
     daughters
    0.36
    sons
    0.29
    children
    0.29
     boys
    0.29
     Sons
    0.28
     Children
    0.28
     biological
    0.27
    Children
    0.25
    Act Density 0.059%

    No Known Activations