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

    Neuronpedia

    INDEX
    Explanations

    references to laundry-related terms, specifically the word "laundry" and its variations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     poffible
    -0.68
     Mera
    -0.63
    yszer
    -0.62
    "],
    -0.61
     Normdatei
    -0.61
    enapa
    -0.61
    chery
    -0.60
     fubject
    -0.60
    ayaquil
    -0.57
     poffe
    -0.57
    POSITIVE LOGITS
    fang
    0.81
     retainer
    0.78
     regurg
    0.65
     Über
    0.64
    bord
    0.63
    ceq
    0.62
    INSTANCE
    0.61
    udge
    0.60
     Arjuna
    0.59
     Nader
    0.58
    Act Density 0.073%

    No Known Activations