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

    Neuronpedia

    INDEX
    Explanations

    references to political or historical conflicts and resolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riott
    -0.16
    erah
    -0.15
    ément
    -0.15
    egas
    -0.14
    ieux
    -0.14
    utz
    -0.14
    enaire
    -0.14
    _ABI
    -0.14
    ierz
    -0.14
    uka
    -0.14
    POSITIVE LOGITS
    Previous
    0.16
    ugu
    0.14
    ảnh
    0.14
    st
    0.14
    å¾
    0.14
     otherwise
    0.14
     previous
    0.14
    andi
    0.14
    á»ķi
    0.13
    ops
    0.13
    Act Density 0.118%

    No Known Activations