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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mathematical operations and rounding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    骨
    -0.43
    disha
    -0.43
     kia
    -0.42
    strptime
    -0.40
    tides
    -0.40
    bri
    -0.39
    hadas
    -0.39
     getStatus
    -0.39
    టి
    -0.38
    ليب
    -0.38
    POSITIVE LOGITS
     accuracy
    1.72
     precision
    1.61
     Accuracy
    1.44
    precision
    1.39
    Precision
    1.37
     Precision
    1.34
    accuracy
    1.32
    Accuracy
    1.30
     accurate
    1.29
     ACCUR
    1.23
    Act Density 0.455%

    No Known Activations