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

    Neuronpedia

    INDEX
    Explanations

    titles and positions related to government and political roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igne
    -0.16
    oren
    -0.15
    iers
    -0.15
    ÏĥÏĦαν
    -0.14
     Delegate
    -0.14
    hof
    -0.13
    jn
    -0.13
    np
    -0.13
    мп
    -0.13
     np
    -0.13
    POSITIVE LOGITS
     Rehab
    0.17
     invol
    0.15
    à¹Īวà¸ĩ
    0.14
    sson
    0.14
    astle
    0.14
    ekim
    0.14
    race
    0.13
    γÏīν
    0.13
    ìĶ¨
    0.13
    Race
    0.13
    Act Density 0.063%

    No Known Activations