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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with descriptive or academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heimer
    -0.17
    asio
    -0.17
    à¥įदर
    -0.15
    /Gate
    -0.15
    lim
    -0.14
    hek
    -0.14
    ضة
    -0.14
     Tun
    -0.14
    daÅŁ
    -0.14
    plen
    -0.14
    POSITIVE LOGITS
    ereum
    0.18
    oren
    0.16
    erval
    0.15
    elo
    0.14
    576
    0.14
    MLE
    0.14
    KL
    0.14
     cellForRowAt
    0.14
    ça
    0.14
     nhau
    0.13
    Act Density 0.002%

    No Known Activations