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

    Neuronpedia

    INDEX
    Explanations

    words and phrases signifying actions, constants, or common references in contexts of human experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enti
    -0.17
    èĭĹ
    -0.15
    antics
    -0.15
    urar
    -0.15
    ILON
    -0.14
    olland
    -0.14
    oser
    -0.14
    unic
    -0.13
     Watkins
    -0.13
    obra
    -0.13
    POSITIVE LOGITS
    .ask
    0.16
    esome
    0.16
    umont
    0.15
     ControllerBase
    0.14
    .Suppress
    0.14
    ROUGH
    0.14
     ç±
    0.14
    stav
    0.14
    ghan
    0.14
    Ãį
    0.14
    Act Density 0.001%

    No Known Activations