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

    Neuronpedia

    INDEX
    Explanations

    mentions of sources or origins of samples in a research context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    #
    -0.61
     pras
    -0.60
     Италијани
    -0.57
    digans
    -0.56
    PreferredItem
    -0.56
    AsUp
    -0.56
     SAX
    -0.55
    }".
    -0.53
     متعلقه
    -0.53
     Salve
    -0.53
    POSITIVE LOGITS
     automatiques
    0.58
    Spoljašnje
    0.53
    baum
    0.53
     identical
    0.52
    monių
    0.52
     lemn
    0.51
    المشاركات
    0.51
     dedans
    0.50
    رامی
    0.49
    InSection
    0.49
    Act Density 0.029%

    No Known Activations