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

    Neuronpedia

    INDEX
    Explanations

    the word "what" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andest
    -0.17
    ongyang
    -0.17
    lue
    -0.16
    ipp
    -0.15
    Ø´ÙĪ
    -0.15
    onaut
    -0.15
    ollo
    -0.14
    ERTICAL
    -0.14
    ække
    -0.14
    ixon
    -0.14
    POSITIVE LOGITS
     he
    0.16
    cheon
    0.15
    cht
    0.15
     Cum
    0.15
    thetic
    0.15
     next
    0.15
    oth
    0.14
    Cum
    0.14
    cord
    0.14
    èĴĤ
    0.14
    Act Density 0.076%

    No Known Activations