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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements expressed in terms of square footage

    oai_token-act-pair · gpt-3.5-turbo

    references to square footage measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.76
     Claus
    -0.74
     Seller
    -0.69
     Petr
    -0.69
     Barcl
    -0.69
     Eug
    -0.64
    ARP
    -0.63
     Rosa
    -0.62
    erer
    -0.62
     Honour
    -0.62
    POSITIVE LOGITS
    pees
    0.91
    µ
    0.86
    feet
    0.86
     Flavoring
    0.81
     Feet
    0.81
    åĨ
    0.80
     meters
    0.77
    ©¶æ¥µ
    0.77
     kilometres
    0.76
     metres
    0.75
    Act Density 0.010%

    No Known Activations