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

    Neuronpedia

    INDEX
    Explanations

    quantities or numeric expressions in varied contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     <=",
    -0.65
     تضيفلها
    -0.62
    ]='\
    -0.56
    AlterField
    -0.56
     resourceCulture
    -0.56
     onCreateView
    -0.55
    aspectj
    -0.54
     surla
    -0.54
     estekak
    -0.52
    TagMode
    -0.52
    POSITIVE LOGITS
     Drexel
    0.52
    uresti
    0.50
    pagation
    0.49
    申し上げます
    0.49
    createNewFile
    0.47
    cektir
    0.46
    addLast
    0.46
     päivä
    0.46
    ArrowToggle
    0.45
     trefoil
    0.45
    Act Density 0.155%

    No Known Activations