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

    Neuronpedia

    INDEX
    Explanations

    specific parts of a building, such as "roof," "rooftops," and "roofing materials."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "roof" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MacArthur
    -0.79
    avez
    -0.73
     Sacrament
    -0.72
     Lauder
    -0.71
    ISTER
    -0.66
     Schumer
    -0.65
    amate
    -0.65
    asure
    -0.63
    bourg
    -0.62
    imens
    -0.62
    POSITIVE LOGITS
     roof
    1.00
    deck
    0.96
     rack
    0.86
    ilion
    0.86
     terr
    0.84
    miah
    0.84
    heed
    0.83
     tops
    0.81
    stairs
    0.81
     loft
    0.81
    Act Density 0.012%

    No Known Activations