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

    Neuronpedia

    INDEX
    Explanations

    the word "all" when it functions as an emphasis indicator or determiner

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.75
    зулта
    -0.74
     Myself
    -0.71
    DoubleQuotes
    -0.71
    unlimited
    -0.70
     esternos
    -0.69
     Cæsar
    -0.69
    myself
    -0.67
     myself
    -0.65
    المناصب
    -0.65
    POSITIVE LOGITS
     some
    0.59
     algunos
    0.52
     “
    0.49
     parts
    0.49
    Algunos
    0.49
    RegressionTest
    0.48
    ContentLoaded
    0.47
    querySelectorAll
    0.47
    肉
    0.46
    {#
    0.45
    Act Density 0.027%

    No Known Activations