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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical norms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Scherer
    -0.81
     Rosal
    -0.78
    合衆
    -0.77
     Phelps
    -0.75
     pittura
    -0.72
     Heidelberg
    -0.70
    Hauptartikel
    -0.70
    </i>
    -0.69
     Spal
    -0.69
     Stapleton
    -0.69
    POSITIVE LOGITS
     norm
    1.23
    norm
    1.14
     Norm
    1.14
     norms
    1.11
    Norm
    1.09
    norms
    0.92
    ArrowToggle
    0.84
     normative
    0.83
     NORM
    0.82
    NORM
    0.77
    Act Density 0.007%

    No Known Activations