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

    Neuronpedia

    INDEX
    Explanations

    references to government or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cop
    -0.16
    éĭ
    -0.16
     cop
    -0.15
    659
    -0.15
    à¸Ķย
    -0.15
    imes
    -0.15
    odb
    -0.14
    ิà¸ĩ
    -0.14
    ibaba
    -0.14
    ibil
    -0.14
    POSITIVE LOGITS
    ance
    0.23
    ment
    0.22
     ern
    0.21
    vern
    0.20
    atore
    0.20
    ãĥ¡ãĥ³ãĥĪ
    0.20
    atorial
    0.18
    enance
    0.18
    ments
    0.18
    ador
    0.18
    Act Density 0.017%

    No Known Activations