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

    Neuronpedia

    INDEX
    Explanations

    numerical values, specifically counts and measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Numb
    -0.62
     Wicidata
    -0.57
     QUANT
    -0.56
    PROLOG
    -0.55
    URLException
    -0.55
     numb
    -0.54
    CollectionUtils
    -0.54
    lynol
    -0.54
     numbers
    -0.54
     amounts
    -0.54
    POSITIVE LOGITS
    endregion
    0.64
    autoconfigure
    0.56
    intios
    0.56
     EconPapers
    0.56
     slightest
    0.54
    qrstuvwxyz
    0.54
    ftagPool
    0.54
     vedi
    0.54
     Besten
    0.53
     hyvä
    0.52
    Act Density 0.025%

    No Known Activations