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

    Neuronpedia

    INDEX
    Explanations

    references to breast cancer and breastfeeding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eof
    -0.15
    hiro
    -0.14
    emez
    -0.14
    ิà¸Ĭ
    -0.14
    ırak
    -0.14
     ç¿
    -0.14
    arpa
    -0.14
    rtle
    -0.14
    .encoding
    -0.14
    rine
    -0.14
    POSITIVE LOGITS
     milk
    0.22
    aurant
    0.22
     breast
    0.22
    bone
    0.22
     Breast
    0.20
    feeding
    0.19
    aurants
    0.19
    bre
    0.18
     Milk
    0.18
     cancer
    0.18
    Act Density 0.005%

    No Known Activations