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

    Neuronpedia

    INDEX
    Explanations

    references to national security and national interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursing
    -0.67
     AMEND
    -0.67
     Assad
    -0.67
     somme
    -0.65
     Juve
    -0.64
     Âge
    -0.64
     posé
    -0.63
     turístico
    -0.63
     impeller
    -0.63
    urbing
    -0.60
    POSITIVE LOGITS
     National
    1.44
     national
    1.42
    NATIONAL
    1.38
    National
    1.33
    national
    1.33
     NATIONAL
    1.17
     nationals
    1.14
    Nationale
    0.98
     nationale
    0.97
     nacionais
    0.96
    Act Density 0.055%

    No Known Activations