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

    Neuronpedia

    INDEX
    Explanations

    interrogative punctuation and question formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avis
    -0.18
    rek
    -0.17
    ichte
    -0.16
    mand
    -0.14
    .omg
    -0.14
    浪
    -0.14
    سÛĮÙĨ
    -0.14
    inea
    -0.14
    å¸
    -0.13
    orget
    -0.13
    POSITIVE LOGITS
    swer
    0.19
    strup
    0.18
     Hra
    0.17
    ¦
    0.17
    isci
    0.16
    swick
    0.15
    ë°ľ
    0.14
    ãĢĩ
    0.14
     responds
    0.14
    pent
    0.14
    Act Density 0.041%

    No Known Activations