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

    Neuronpedia

    INDEX
    Explanations

    references to government departments and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anj
    -0.15
    imar
    -0.15
    祥
    -0.14
    å¦ĥ
    -0.14
    泡
    -0.14
    ilet
    -0.14
    à¥Ģब
    -0.13
    CESS
    -0.13
     åĪ¶
    -0.13
    ovenant
    -0.13
    POSITIVE LOGITS
     Defense
    0.31
     Homeland
    0.29
     Commerce
    0.28
     Labor
    0.28
    Hom
    0.27
     Justice
    0.27
    Defense
    0.27
     Veterans
    0.26
     Housing
    0.26
     Treasury
    0.26
    Act Density 0.017%

    No Known Activations