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

    Neuronpedia

    INDEX
    Explanations

    words related to cleanliness and hygiene

    oai_token-act-pair · gpt-3.5-turbo

    references to cleanliness or purity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.89
    doms
    -0.86
    Reloaded
    -0.80
    PsyNetMessage
    -0.76
    CVE
    -0.73
    pheus
    -0.72
    MAC
    -0.70
    ãĥĦ
    -0.70
     htt
    -0.69
    ENTS
    -0.68
    POSITIVE LOGITS
    liness
    1.23
    clean
    0.91
     slate
    0.90
     linen
    0.90
     cleaner
    0.88
     clean
    0.86
    se
    0.83
     Clean
    0.80
    houses
    0.78
    ly
    0.76
    Act Density 0.013%

    No Known Activations