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

    Neuronpedia

    INDEX
    Explanations

    references to historical rulers and their reigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Special
    -0.14
    alent
    -0.13
     Mos
    -0.13
    aub
    -0.13
    EMPLARY
    -0.13
     Reporting
    -0.13
    å¡ļ
    -0.13
     EntityState
    -0.13
     Pace
    -0.13
     svob
    -0.12
    POSITIVE LOGITS
     reign
    0.31
     Reign
    0.27
     reigning
    0.27
     monarch
    0.27
     ruler
    0.27
     rule
    0.25
     rulers
    0.25
     ruling
    0.25
     king
    0.24
     throne
    0.24
    Act Density 0.097%

    No Known Activations