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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "compute" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </b>
    -0.81
     Kral
    -0.78
    newArray
    -0.72
     Paraguay
    -0.72
     Caw
    -0.72
     Jeanette
    -0.71
     houſe
    -0.71
     Milner
    -0.69
     McGregor
    -0.67
     Sarm
    -0.66
    POSITIVE LOGITS
    bidities
    0.88
     computed
    0.86
    Độ
    0.83
    computed
    0.82
    webElementXpaths
    0.81
    tfrac
    0.79
    Compute
    0.79
     régal
    0.78
    oblotting
    0.78
     Compute
    0.77
    Act Density 0.121%

    No Known Activations