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

    Neuronpedia

    INDEX
    Explanations

    words related to physical locations, specifically focusing on floors

    oai_token-act-pair · gpt-3.5-turbo

    references to "floor" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.66
    eness
    -0.64
    elson
    -0.63
     ALS
    -0.62
     Alonso
    -0.62
    addon
    -0.59
    lez
    -0.59
    acca
    -0.58
     Walters
    -0.57
    laus
    -0.57
    POSITIVE LOGITS
    floor
    1.19
     floor
    1.16
     Floor
    1.14
     floors
    1.00
     mats
    0.94
    boards
    0.93
     ceiling
    0.88
     carpet
    0.87
     rug
    0.86
    tops
    0.83
    Act Density 0.012%

    No Known Activations