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

    Neuronpedia

    INDEX
    Explanations

    questions about causation and evidence in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whenever
    -0.15
    ÑĨÑİ
    -0.15
     precios
    -0.15
    istique
    -0.14
    yl
    -0.14
    ulin
    -0.14
    culate
    -0.14
    æ¦ľ
    -0.14
     Wend
    -0.13
    PDOException
    -0.13
    POSITIVE LOGITS
     or
    0.18
     yoksa
    0.16
     something
    0.15
     etc
    0.15
    è¿ĺæĺ¯
    0.15
    kip
    0.14
    elian
    0.14
    avian
    0.14
     oder
    0.14
    519
    0.14
    Act Density 0.061%

    No Known Activations