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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identifying special occurrences or exceptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.65
     تضيفلها
    -0.64
     متعلقه
    -0.63
    Cyfeiriadau
    -0.59
     Spisak
    -0.59
    UnusedPrivate
    -0.56
     estekak
    -0.54
    Geplaatst
    -0.53
    Atsauces
    -0.52
     raiſ
    -0.52
    POSITIVE LOGITS
     even
    0.66
    owns
    0.56
    even
    0.55
     Even
    0.55
    Even
    0.54
     CanadaChoose
    0.54
     giản
    0.54
     Kut
    0.52
    stylesheet
    0.52
     EconPapers
    0.50
    Act Density 0.091%

    No Known Activations