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

    Neuronpedia

    INDEX
    Explanations

    references to the implementation and effects of regulations or laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quests
    -0.16
    oman
    -0.15
    ongo
    -0.15
    issions
    -0.15
    straints
    -0.14
    обÑĭÑĤи
    -0.13
    eses
    -0.13
    ãĥĸãĥª
    -0.13
    _ISS
    -0.13
    hints
    -0.13
    POSITIVE LOGITS
    ître
    0.18
    ilor
    0.17
    γε
    0.16
    lle
    0.15
    enville
    0.14
    reads
    0.14
     Wonderland
    0.14
    reesome
    0.14
     implementation
    0.14
    ograd
    0.14
    Act Density 0.038%

    No Known Activations