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

    Neuronpedia

    INDEX
    Explanations

    labels and sections typically found in a table of contents or index, indicating the structure of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stown
    -0.07
    mitted
    -0.06
    ýt
    -0.06
     undo
    -0.06
    erspective
    -0.06
    itecture
    -0.06
    vers
    -0.06
    eting
    -0.05
    éo
    -0.05
     \"
    -0.05
    POSITIVE LOGITS
    аÑĢод
    0.07
    ofire
    0.06
    uxe
    0.06
    leans
    0.06
    INTR
    0.06
     ëĭ
    0.06
     Ill
    0.06
    _CSR
    0.06
     âĸ¼
    0.06
    ORIES
    0.06
    Act Density 0.003%

    No Known Activations