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

    Neuronpedia

    INDEX
    Explanations

    tokens representing numerical data or terms related to sequences and mathematical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.97
     Wikimedijinoj
    -0.76
     AssemblyCompany
    -0.75
     surla
    -0.73
    UVWXYZ
    -0.72
    enderror
    -0.71
    moiselle
    -0.69
    afficheront
    -0.68
    انجليز
    -0.68
     censiti
    -0.67
    POSITIVE LOGITS
     num
    0.57
    num
    0.55
     numerus
    0.54
     numbers
    0.51
     fib
    0.51
     number
    0.50
    Num
    0.49
    fib
    0.47
     fan
    0.44
     nombre
    0.43
    Act Density 1.323%

    No Known Activations