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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.61
     Drapeau
    -0.57
    thâu
    -0.55
    TagMode
    -0.55
    ArrowToggle
    -0.55
    RegressionTest
    -0.55
    imura
    -0.54
    ervor
    -0.54
    setter
    -0.54
    EnableWeb
    -0.53
    POSITIVE LOGITS
     parlant
    0.61
     religieuses
    0.61
     fermés
    0.60
     vastaan
    0.58
     concernés
    0.57
     betrokken
    0.56
     Pyrr
    0.56
    الحياه
    0.55
     läsa
    0.55
     privilégi
    0.55
    Act Density 0.295%

    No Known Activations