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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate connections or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertas
    -0.16
    pek
    -0.16
    esen
    -0.15
    uez
    -0.15
    ungan
    -0.14
    ument
    -0.14
    keit
    -0.13
    pard
    -0.13
    rozen
    -0.13
    QUIRES
    -0.13
    POSITIVE LOGITS
    λο
    0.14
     درÛĮ
    0.14
    hou
    0.14
     Sphinx
    0.13
    BlockSize
    0.13
    erland
    0.13
     oto
    0.13
    VO
    0.13
     Mastery
    0.13
    PRS
    0.13
    Act Density 0.400%

    No Known Activations