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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive outcomes and improvements over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    openConnection
    -0.61
     Celui
    -0.54
    ulx
    -0.54
    Hands
    -0.53
     scattata
    -0.51
     whereof
    -0.50
    SPATH
    -0.48
    BeginContext
    -0.47
     Duft
    -0.46
    ngOnInit
    -0.46
    POSITIVE LOGITS
    queryInterface
    0.78
     estimés
    0.62
    SequentialGroup
    0.62
    ThroughAttribute
    0.61
    StoreMessageInfo
    0.60
     désolés
    0.58
     gradually
    0.58
    Expected
    0.58
     ffilmiau
    0.58
    Eventually
    0.57
    Act Density 0.296%

    No Known Activations