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

    Neuronpedia

    INDEX
    Explanations

    references to a specific architectural or programmatic element, likely related to code or user interface layout

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    lia
    -0.78
    BeginContext
    -0.73
     везе
    -0.67
     BoxFit
    -0.66
    breakpoints
    -0.65
     оригіналу
    -0.63
    LIA
    -0.59
    Datuak
    -0.55
    BeginInit
    -0.54
    anı
    -0.54
    POSITIVE LOGITS
    aria
    2.73
    ARIA
    1.92
    arias
    1.19
    ariah
    0.99
     aria
    0.98
    ária
    0.95
    Aria
    0.86
    ariam
    0.84
    ària
    0.82
    ariya
    0.78
    Act Density 0.001%

    No Known Activations