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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "and" as well as variations indicating collective or additive relationships among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.83
    PreferredItem
    -0.81
    MessageOf
    -0.62
     ujednoznacz
    -0.58
    万円
    -0.58
    SequentialGroup
    -0.58
     AssemblyProduct
    -0.57
     Communism
    -0.57
    geord
    -0.56
     Мексичка
    -0.55
    POSITIVE LOGITS
     fellow
    0.64
    はじめに
    0.64
     myself
    0.64
     who
    0.61
     young
    0.61
     younger
    0.60
     senior
    0.60
     professional
    0.60
     whom
    0.57
     whome
    0.57
    Act Density 0.315%

    No Known Activations