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

    Neuronpedia

    INDEX
    Explanations

    phrases related to structural or organizational relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wap
    -0.17
     Wire
    -0.15
    OA
    -0.15
    akat
    -0.14
    atron
    -0.14
    ·æĸ°
    -0.14
    villa
    -0.14
    ç«ĭ
    -0.14
    emez
    -0.14
    olet
    -0.14
    POSITIVE LOGITS
    adge
    0.15
    ÏĦÏģι
    0.15
    icos
    0.14
     Cop
    0.14
    ãĥ¼ãĥª
    0.14
    -tests
    0.14
    ufs
    0.13
    opes
    0.13
     ä½ĵ
    0.13
    urement
    0.13
    Act Density 0.226%

    No Known Activations