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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting elements and mathematical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lfw
    -0.16
    light
    -0.15
    reich
    -0.15
    ytt
    -0.15
    oda
    -0.15
    yms
    -0.14
    innen
    -0.14
     Lind
    -0.14
    еÑĢин
    -0.14
    ÄĽn
    -0.13
    POSITIVE LOGITS
    *[
    0.17
    DED
    0.16
    TES
    0.15
    otics
    0.15
    íĦ
    0.15
    ีà¸Ķ
    0.15
    vana
    0.14
    ande
    0.14
    [-
    0.14
    Deque
    0.14
    Act Density 0.017%

    No Known Activations