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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and data metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kegaard
    -0.52
    hiya
    -0.42
    phite
    -0.42
    :✨
    -0.41
    neden
    -0.40
    URLException
    -0.40
    rzez
    -0.39
    ută
    -0.39
     Bea
    -0.39
    pidou
    -0.38
    POSITIVE LOGITS
     number
    2.39
    number
    2.01
     Number
    1.87
     count
    1.84
     NUMBER
    1.82
     Anzahl
    1.82
    Number
    1.81
     aantal
    1.79
     número
    1.77
     numbers
    1.76
    Act Density 1.220%

    No Known Activations