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

    Neuronpedia

    INDEX
    Explanations

    expressions of awe or wonder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SCO
    -0.15
    vestment
    -0.15
    agn
    -0.15
    rgan
    -0.15
    ãĥ¼ãĤ¿ãĥ¼
    -0.14
    ูà¸Ļ
    -0.14
    alk
    -0.14
    je
    -0.14
    openh
    -0.14
     jo
    -0.13
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¸Īำ
    0.15
     ìĨ¡
    0.14
    fully
    0.14
    åıĤçħ§
    0.13
    \CMS
    0.13
    ROL
    0.13
    Pad
    0.13
     Pill
    0.13
     Spear
    0.13
     Patri
    0.13
    Act Density 0.001%

    No Known Activations