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

    Neuronpedia

    INDEX
    Explanations

    assertions of correctness and validation in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoreMessageInfo
    -0.79
     مشين
    -0.70
    expandindo
    -0.66
     Biôgrafia
    -0.62
    IUrlHelper
    -0.62
     Udo
    -0.61
    titleMargin
    -0.58
    URIComponent
    -0.58
     архивлан
    -0.58
    NameInMap
    -0.58
    POSITIVE LOGITS
     vrai
    0.69
     vraie
    0.63
    没错
    0.61
    MessageTagHelper
    0.59
     mosca
    0.56
     profundas
    0.54
     prophetic
    0.54
     faits
    0.53
     correta
    0.53
     thèse
    0.52
    Act Density 0.338%

    No Known Activations