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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equalities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.08
     дописавши
    -1.06
     autorytatywna
    -1.00
    AccessorTable
    -0.99
     виправивши
    -0.91
    InjectAttribute
    -0.90
     bezeichneter
    -0.88
     ویکی‌پدیای
    -0.87
    цездатний
    -0.87
    دانشنامهٔ
    -0.85
    POSITIVE LOGITS
    baomidou
    0.58
     +
    0.54
    </strong>
    0.52
    '
    0.49
    </em>
    0.49
    "
    0.48
     /
    0.47
     [
    0.47
    ROIT
    0.46
    2
    0.46
    Act Density 0.025%

    No Known Activations