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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or factors leading to specific outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lenker
    -0.72
    ContentAsync
    -0.66
    dequeue
    -0.58
    BeginInit
    -0.57
    <?
    -0.56
    theless
    -0.54
    #
    -0.54
    Välislingid
    -0.54
    endregion
    -0.53
     retired
    -0.53
    POSITIVE LOGITS
     caused
    2.86
    caused
    2.64
     Caused
    2.30
     occasioned
    1.81
     triggered
    1.76
     causado
    1.71
     induced
    1.64
     provocado
    1.54
     sparked
    1.51
     spowod
    1.50
    Act Density 0.185%

    No Known Activations