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

    Neuronpedia

    INDEX
    Explanations

    lines of code involving integer constant definitions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.85
     propOrder
    -0.68
     intptr
    -0.62
     صوتيه
    -0.57
    RegistryLite
    -0.55
     незавершена
    -0.52
    ittäin
    -0.51
    hdl
    -0.50
     betweenstory
    -0.50
    INSTALLED
    -0.49
    POSITIVE LOGITS
    INT
    2.48
     INT
    1.70
    INTS
    0.91
    INTEN
    0.90
    inten
    0.83
    UINT
    0.75
    intended
    0.70
    inty
    0.69
    endpush
    0.66
    INTA
    0.64
    Act Density 0.002%

    No Known Activations