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

    Neuronpedia

    INDEX
    Explanations

    references to historical political systems and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¨İ
    -0.16
    iem
    -0.15
     cap
    -0.14
    uko
    -0.14
    oshi
    -0.14
    à¤Łà¤°
    -0.14
    .nano
    -0.13
    oha
    -0.13
    ä¿ĿæĬ¤
    -0.13
    neh
    -0.13
    POSITIVE LOGITS
     Stalin
    0.19
     Lenin
    0.16
     Soviet
    0.16
     centrally
    0.14
    erdale
    0.14
     Pablo
    0.14
     Reporting
    0.13
    Len
    0.13
     bure
    0.13
    workers
    0.13
    Act Density 0.115%

    No Known Activations