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

    Neuronpedia

    INDEX
    Explanations

    expressions related to interpretation or understanding

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.87
    ThroughAttribute
    -0.84
    GraphicsUnit
    -0.80
    EUROPA
    -0.77
     initComponents
    -0.77
    Билгалдахарш
    -0.77
    Rüyada
    -0.76
     дописавши
    -0.73
    QMetaType
    -0.73
    addContainerGap
    -0.71
    POSITIVE LOGITS
     meaning
    0.59
     sense
    0.56
     polega
    0.52
     Fällen
    0.52
     смысле
    0.50
    Locke
    0.50
     Plin
    0.50
    meaning
    0.50
     Malin
    0.49
     kéo
    0.49
    Act Density 0.007%

    No Known Activations