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

    Neuronpedia

    INDEX
    Explanations

    the square root of numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to square measurements or geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARP
    -0.77
    oan
    -0.66
     Claus
    -0.65
    INA
    -0.65
     Gloss
    -0.63
    ICT
    -0.62
     Seller
    -0.60
     appropri
    -0.59
    bach
    -0.59
     confidentiality
    -0.59
    POSITIVE LOGITS
     Enix
    1.12
     square
    0.84
    square
    0.82
     squares
    0.80
    ³
    0.79
    Square
    0.78
    µ
    0.78
    feet
    0.78
    pees
    0.76
     kilomet
    0.72
    Act Density 0.010%

    No Known Activations