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

    Neuronpedia

    INDEX
    Explanations

    references to Russia and related political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.51
    thâu
    -0.48
    RegressionTest
    -0.44
     Sola
    -0.43
    Gambas
    -0.42
    
    -0.42
     ligiloj
    -0.42
    insic
    -0.41
    請繼續往下閱讀
    -0.41
    Rhestr
    -0.41
    POSITIVE LOGITS
     Ukraine
    1.40
     Moscow
    1.38
     Putin
    1.38
     Russia
    1.37
     Russian
    1.34
     Kiev
    1.30
    Moscow
    1.29
    Putin
    1.28
     Kyiv
    1.28
     Kremlin
    1.27
    Act Density 1.815%

    No Known Activations