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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges that indicate dates or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    алеж
    -0.15
    ulk
    -0.15
    ocre
    -0.14
    па
    -0.14
    wers
    -0.14
    judul
    -0.14
     Interior
    -0.14
    abol
    -0.14
    ickey
    -0.14
    itou
    -0.14
    POSITIVE LOGITS
     Unblock
    0.16
    iness
    0.15
    ness
    0.15
    ayne
    0.15
    Ïģιν
    0.14
    彦
    0.14
    NESS
    0.14
     tem
    0.13
     EIF
    0.13
     Receipt
    0.13
    Act Density 0.018%

    No Known Activations