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

    Neuronpedia

    INDEX
    Explanations

    references to political actions and international relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    639
    -0.15
    517
    -0.14
    dete
    -0.14
    пÑĢиклад
    -0.13
     Masc
    -0.13
    경기
    -0.13
     BUF
    -0.13
    ichel
    -0.13
    οÏħÏģγ
    -0.13
    را
    -0.13
    POSITIVE LOGITS
     State
    0.39
    State
    0.31
     Secretary
    0.27
     Fog
    0.27
     Pentagon
    0.26
    -State
    0.26
     administration
    0.25
     White
    0.25
     CENT
    0.24
     secretary
    0.24
    Act Density 0.099%

    No Known Activations