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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the degree of impact or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.16
    身ä¸Ĭ
    -0.16
     ob
    -0.15
    inya
    -0.14
    duct
    -0.14
    vale
    -0.14
    ebb
    -0.14
    inen
    -0.14
    357
    -0.14
     fare
    -0.14
    POSITIVE LOGITS
    aeda
    0.16
    qus
    0.15
    istar
    0.14
     whether
    0.14
    _rhs
    0.14
    adt
    0.14
     expansion
    0.14
    isto
    0.14
     hears
    0.13
    ạo
    0.13
    Act Density 0.218%

    No Known Activations