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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and household roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oftware
    -0.14
    zik
    -0.14
    ruc
    -0.14
    hung
    -0.14
    شر
    -0.13
    Deque
    -0.13
    imately
    -0.13
    .partner
    -0.13
    icipant
    -0.13
     Shelter
    -0.13
    POSITIVE LOGITS
     servants
    0.39
     domest
    0.35
     servant
    0.35
     household
    0.33
     domestic
    0.30
     ma
    0.30
    serv
    0.30
     cook
    0.29
     Household
    0.28
     maid
    0.28
    Act Density 0.233%

    No Known Activations