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

    Neuronpedia

    INDEX
    Explanations

    references to political or economic entities and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FirebaseAuth
    -0.31
     Profit
    -0.31
     prest
    -0.31
     Cater
    -0.30
     plat
    -0.30
    mail
    -0.30
     quanti
    -0.29
     quan
    -0.29
    MutableLiveData
    -0.29
     greater
    -0.29
    POSITIVE LOGITS
     countries
    0.74
     Countries
    0.65
     nations
    0.65
    Countries
    0.64
     países
    0.63
     naciones
    0.60
    countries
    0.58
     paesi
    0.58
    ArrowToggle
    0.57
     OMITBAD
    0.57
    Act Density 0.147%

    No Known Activations