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

    Neuronpedia

    INDEX
    Explanations

    details related to scientific research and experimental methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ottie
    -0.15
    ηÏĤ
    -0.14
    ati
    -0.13
    æĿĤ
    -0.13
    ivol
    -0.13
    ect
    -0.13
    apes
    -0.13
    ãĥ¥
    -0.13
    AZY
    -0.12
    ázev
    -0.12
    POSITIVE LOGITS
     special
    0.53
    special
    0.44
    çī¹æ®Ĭ
    0.41
     ÑģпеÑĨÑĸ
    0.36
     ÑģпеÑĨи
    0.35
     specialized
    0.35
    -special
    0.34
     spécial
    0.34
    Special
    0.34
     SPECIAL
    0.34
    Act Density 0.446%

    No Known Activations