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

    Neuronpedia

    INDEX
    Explanations

    specific relationships or connections in structured data or texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HasIndex
    -0.56
    Necesito
    -0.56
    LEZ
    -0.52
     geslacht
    -0.52
    QWidget
    -0.49
    くださいませ
    -0.48
    ++]=
    -0.48
    hams
    -0.47
    jface
    -0.47
     føl
    -0.47
    POSITIVE LOGITS
     respectively
    1.20
    respectively
    1.11
     respective
    1.02
     rispet
    0.98
     masing
    0.94
     respectivamente
    0.93
     respectivement
    0.92
    それぞれ
    0.88
    各自
    0.77
     jeweils
    0.77
    Act Density 0.694%

    No Known Activations