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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical structures, especially roofs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of roofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.86
     MacArthur
    -0.79
    avez
    -0.78
    inational
    -0.72
     Schumer
    -0.72
    emonic
    -0.69
    nesia
    -0.68
     ALS
    -0.67
    ppe
    -0.65
     Holden
    -0.65
    POSITIVE LOGITS
     roof
    0.97
    deck
    0.94
     terr
    0.93
     ornament
    0.90
     tops
    0.89
     rack
    0.89
    ed
    0.83
    buster
    0.81
     canopy
    0.81
     racks
    0.80
    Act Density 0.032%

    No Known Activations