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

    Neuronpedia

    INDEX
    Explanations

    references to cabinets or cabinet members in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordin
    -0.18
    ument
    -0.18
    utenberg
    -0.17
     cá
    -0.17
    icast
    -0.16
    _ONCE
    -0.15
    edom
    -0.15
    ÑģÑı
    -0.15
    -factor
    -0.15
    uments
    -0.14
    POSITIVE LOGITS
    maker
    0.20
    éĸĢ
    0.19
    ted
    0.19
     doors
    0.19
    -level
    0.18
    makers
    0.18
    rio
    0.18
     door
    0.17
    .gdx
    0.17
    tc
    0.17
    Act Density 0.011%

    No Known Activations