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

    Neuronpedia

    INDEX
    Explanations

    references to international military or political dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demokrat
    -0.16
    .Atomic
    -0.15
    Lead
    -0.15
    .apple
    -0.15
    chwitz
    -0.15
    celik
    -0.15
     Lead
    -0.14
    measurement
    -0.14
    fik
    -0.14
    aras
    -0.14
    POSITIVE LOGITS
     ex
    0.17
     пÑĢоз
    0.16
    loy
    0.16
     Interior
    0.16
    hawk
    0.15
     Sole
    0.15
    857
    0.15
     local
    0.15
     security
    0.15
     nomin
    0.14
    Act Density 0.045%

    No Known Activations