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

    Neuronpedia

    INDEX
    Explanations

    references to footnotes in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     liever
    -0.66
     sauvages
    -0.64
     veneta
    -0.64
     lisse
    -0.63
     quæ
    -0.62
     veux
    -0.60
     fuoco
    -0.60
    e
    -0.60
     almas
    -0.59
     Evangelio
    -0.59
    POSITIVE LOGITS
    Footnote
    1.30
    footnote
    1.17
     Footnote
    1.16
     footnote
    1.11
    footnotes
    1.09
     footnotes
    1.05
    Footnotes
    0.92
     дописавши
    0.84
     tartalomajánló
    0.82
    UnusedPrivate
    0.81
    Act Density 0.001%

    No Known Activations