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

    Neuronpedia

    INDEX
    Explanations

    language that expresses uncertainty or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =[]
    -0.56
    });*/
    -0.55
     "))
    -0.53
    ”),
    -0.52
     ").
    -0.52
    getActiveSheet
    -0.50
     ")
    -0.50
    )”.
    -0.50
    WaitGroup
    -0.50
    .’”
    -0.49
    POSITIVE LOGITS
     disambiguazione
    0.89
    StoreMessageInfo
    0.64
    matchCondition
    0.64
     дописавши
    0.61
    guien
    0.60
    脚注の使い方
    0.59
     estekak
    0.59
     Somewhere
    0.59
     Recall
    0.58
     فريبيس
    0.58
    Act Density 0.178%

    No Known Activations