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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their connections to text structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.79
    awtextra
    -0.78
     <=",
    -0.76
    WriteBarrier
    -0.74
    RegressionTest
    -0.72
     <>",
    -0.71
    RenderAtEndOf
    -0.67
    principalTable
    -0.67
    AccessorTable
    -0.66
     Réponses
    -0.66
    POSITIVE LOGITS
     gratuits
    0.54
     gratuites
    0.50
    attro
    0.49
     humaine
    0.49
     nivelul
    0.48
     Popis
    0.46
     humaines
    0.46
    thoff
    0.45
     arasındaki
    0.45
     complètes
    0.44
    Act Density 0.771%

    No Known Activations