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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate causation or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.65
    contentLoaded
    -0.62
    LayoutStyle
    -0.61
    下载附件
    -0.57
     neighbour
    -0.55
    createCanvas
    -0.52
    inherited
    -0.52
    WriteLiteral
    -0.52
    neighbour
    -0.52
     propOrder
    -0.51
    POSITIVE LOGITS
    fromnode
    0.72
     Wikimedijinoj
    0.59
     فريبيس
    0.58
     esternos
    0.53
    Buildable
    0.53
     COIN
    0.51
    coin
    0.50
    󠁢
    0.50
    osoba
    0.49
     gynhyrchwyd
    0.49
    Act Density 0.389%

    No Known Activations