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

    Neuronpedia

    INDEX
    Explanations

    concepts related to rules, regulations, or social norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athi
    -0.15
    CHandle
    -0.15
    /MIT
    -0.14
     circum
    -0.14
    Ïİν
    -0.14
     Hay
    -0.14
     Mate
    -0.14
    /***/
    -0.14
    ITLE
    -0.14
    IRM
    -0.13
    POSITIVE LOGITS
    ews
    0.19
    anka
    0.17
    ymous
    0.15
    dt
    0.14
    mps
    0.14
    Ñıк
    0.14
    nees
    0.14
    Rpc
    0.14
    148
    0.13
    anship
    0.13
    Act Density 0.560%

    No Known Activations