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

    Neuronpedia

    INDEX
    Explanations

    terms related to cleanliness or filth, particularly variations of "dirty" and "dirt"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.79
    IMPORTED
    -0.65
    новниш
    -0.62
     disambiguazione
    -0.61
    RefNanny
    -0.60
    RTEE
    -0.59
    IMDG
    -0.55
    babkan
    -0.54
     lenker
    -0.53
     "}";
    -0.52
    POSITIVE LOGITS
     tops
    1.64
     Tops
    1.14
    tops
    1.13
     topping
    1.10
     topped
    1.07
    topped
    0.90
     toppings
    0.87
     bases
    0.83
    topping
    0.78
     dirt
    0.77
    Act Density 0.086%

    No Known Activations