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

    Neuronpedia

    INDEX
    Explanations

    numbers and numerical patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.04
    parsedMessage
    -0.93
    UnsafeEnabled
    -0.92
    complexContent
    -0.89
     propOrder
    -0.85
     كومونز
    -0.84
    ThroughAttribute
    -0.83
    DataPropertyName
    -0.82
    تقاوى
    -0.81
     دیکھیے
    -0.77
    POSITIVE LOGITS
    8
    0.58
    9
    0.55
    7
    0.54
    6
    0.50
    3
    0.46
    5
    0.46
    0
    0.46
    1
    0.44
    4
    0.43
    2
    0.43
    Act Density 0.800%

    No Known Activations