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

    Neuronpedia

    INDEX
    Explanations

    references to entities in a document, particularly pronouns and their antecedents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.56
     EMPLOYEES
    -0.54
     magnético
    -0.54
    unmodifiable
    -0.53
     laude
    -0.53
    aneous
    -0.52
    inergic
    -0.52
    олові
    -0.52
    chränk
    -0.51
     oreille
    -0.51
    POSITIVE LOGITS
    didSet
    0.68
    </caption>
    0.65
     Оно
    0.63
    AndEndTag
    0.60
    DoubleQuotes
    0.57
     وتسجيلات
    0.55
    WebServlet
    0.54
     které
    0.53
    OGND
    0.52
    Referències
    0.52
    Act Density 0.884%

    No Known Activations