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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     andato
    -0.60
     crdi
    -0.57
     ComVisible
    -0.56
     flesta
    -0.56
     cdti
    -0.54
     själva
    -0.54
     tfsi
    -0.52
    swt
    -0.52
     vettor
    -0.52
     vectorielles
    -0.52
    POSITIVE LOGITS
    WriteLiteral
    0.70
    awtextra
    0.68
    aband
    0.64
    XmlAccessorType
    0.61
    ypus
    0.60
    !*\
    0.60
     COMMENTS
    0.59
     ostavi
    0.59
    principalColumn
    0.58
    طل
    0.57
    Act Density 0.035%

    No Known Activations