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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific measurements related to area, such as square feet or square miles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     compr
    -0.61
    intent
    -0.58
    alys
    -0.58
    anwhile
    -0.56
    gotten
    -0.56
    ilyn
    -0.55
     tyr
    -0.54
     Canaver
    -0.54
     licens
    -0.52
    oleon
    -0.52
    POSITIVE LOGITS
    elsius
    0.65
     devoted
    0.63
    ouse
    0.62
     bedrooms
    0.62
     dwellings
    0.62
    houses
    0.61
     apartments
    0.61
    ²
    0.61
     apartment
    0.60
    essions
    0.60
    Act Density 14.584%

    No Known Activations