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

    Neuronpedia

    INDEX
    Explanations

    references to soap and related cleaning products

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ########.
    -0.82
    AsUp
    -0.77
     Kenn
    -0.76
    munk
    -0.76
    AnchorStyles
    -0.71
    Estudios
    -0.71
     BoxFit
    -0.69
     dred
    -0.69
     SEDS
    -0.69
    Kenn
    -0.68
    POSITIVE LOGITS
     soap
    1.91
     Soap
    1.83
     SOAP
    1.70
    soap
    1.63
    Soap
    1.62
    SOAP
    1.53
     soaps
    1.49
     soapy
    1.18
    皂
    1.04
     jabón
    0.90
    Act Density 0.001%

    No Known Activations