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

    Neuronpedia

    INDEX
    Explanations

    words related to domestic roles and household management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zik
    -0.16
    imately
    -0.14
    ruc
    -0.13
    icipant
    -0.13
    ARGS
    -0.13
    cade
    -0.13
    WSTR
    -0.12
    ongan
    -0.12
    ceiver
    -0.12
    croll
    -0.12
    POSITIVE LOGITS
     servants
    0.39
     servant
    0.36
     maid
    0.35
     domest
    0.34
    serv
    0.33
     wait
    0.31
    wait
    0.30
     domestic
    0.29
     ma
    0.29
     cook
    0.29
    Act Density 0.354%

    No Known Activations