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

    Neuronpedia

    INDEX
    Explanations

    descriptive attributes related to comfort and quality of spaces or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.56
    rodo
    -0.55
    tvguidetime
    -0.54
    SourceChecksum
    -0.54
    irse
    -0.52
     thickness
    -0.51
    getWriter
    -0.51
    inalis
    -0.50
    <bos>
    -0.50
    fromnode
    -0.50
    POSITIVE LOGITS
     clean
    1.13
     spacious
    1.07
     imma
    0.93
     spotless
    0.93
     comfortable
    0.92
     Clean
    0.91
     tidy
    0.91
     cleanliness
    0.90
     cleanest
    0.89
     CLEAN
    0.89
    Act Density 0.074%

    No Known Activations