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

    Neuronpedia

    INDEX
    Explanations

    elements or phrases associated with programming or technical elements in documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.17
    inged
    -0.15
    sg
    -0.15
    arring
    -0.15
    gni
    -0.15
    odic
    -0.14
     Duffy
    -0.14
     عبر
    -0.14
     Newton
    -0.14
     ÙĨص
    -0.14
    POSITIVE LOGITS
    å¼±
    0.15
    ACHI
    0.15
    qml
    0.15
    anchise
    0.14
    Ä±ÅŁÄ±k
    0.14
    rosse
    0.14
    ãĤ¯ãĥ©ãĥĸ
    0.14
    achi
    0.13
     latch
    0.13
    /wiki
    0.13
    Act Density 0.002%

    No Known Activations