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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical sets and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    canes
    -0.58
     ویکی‌پدیای
    -0.55
     sebenar
    -0.53
    ToBe
    -0.51
     mere
    -0.50
     zugleich
    -0.49
    iritual
    -0.49
     utama
    -0.49
    grès
    -0.49
     главное
    -0.49
    POSITIVE LOGITS
    subset
    1.57
     subset
    1.26
     subsets
    1.04
    subseteq
    0.90
     handful
    0.88
    ⊂
    0.83
    Subset
    0.81
    NameInMap
    0.79
     dozen
    0.79
    а
    0.76
    Act Density 0.085%

    No Known Activations