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

    Neuronpedia

    INDEX
    Explanations

    qualities related to cleanliness, simplicity, and purity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.63
    GEBURTSDATUM
    -0.62
    zension
    -0.61
    Билгалдахарш
    -0.56
    atile
    -0.54
    Unauthorized
    -0.52
     magnétique
    -0.52
    cussed
    -0.51
     Mehdi
    -0.51
    íble
    -0.51
    POSITIVE LOGITS
     clean
    1.17
     clear
    1.15
     clarity
    1.13
     cleaner
    1.10
     cleanest
    1.10
     Clear
    1.04
     clearest
    1.02
     clearer
    1.01
    cleaner
    0.99
     purity
    0.98
    Act Density 0.352%

    No Known Activations