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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols related to references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pend
    -0.15
    lion
    -0.15
    READING
    -0.14
    ообÑĢаз
    -0.14
     Orn
    -0.14
    oop
    -0.14
    ãĤĮãģ©
    -0.14
    REFERRED
    -0.14
    asca
    -0.13
    anka
    -0.13
    POSITIVE LOGITS
    ulace
    0.15
    tie
    0.15
    587
    0.14
    esse
    0.14
    azer
    0.14
    ëijIJ
    0.14
    uguay
    0.13
    teg
    0.13
    419
    0.13
    gratis
    0.13
    Act Density 0.016%

    No Known Activations