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

    Neuronpedia

    INDEX
    Explanations

    terms related to architectural features or design elements, especially those related to floor structure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.81
    elson
    -0.77
    ortium
    -0.77
    eness
    -0.77
    NULL
    -0.69
    enegger
    -0.69
     Unch
    -0.69
    KEN
    -0.68
     ALS
    -0.68
    eer
    -0.67
    POSITIVE LOGITS
    boards
    1.10
    floor
    1.03
     floor
    1.01
    plan
    0.99
    nuts
    0.98
     Floor
    0.96
    nut
    0.93
     floors
    0.92
    parts
    0.90
     mats
    0.88
    Act Density 0.028%

    No Known Activations