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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.77
    pushFollow
    -0.71
    Datuak
    -0.65
     дописавши
    -0.60
    InjectAttribute
    -0.58
    ViewImports
    -0.57
     sacré
    -0.57
     Paglinawan
    -0.57
     okuyayım
    -0.56
     saja
    -0.55
    POSITIVE LOGITS
    ;?>
    0.57
     Tek
    0.57
    atiz
    0.54
    ябре
    0.54
    分で
    0.54
    spire
    0.54
    =[],
    0.52
     col
    0.52
    oprot
    0.52
    GOTREF
    0.52
    Act Density 0.022%

    No Known Activations