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

    Neuronpedia

    INDEX
    Explanations

    terms related to democracy and its various forms and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PropertyChanging
    -0.77
    NewUrlParser
    -0.64
    Rüyada
    -0.62
     Aene
    -0.61
    chaik
    -0.61
    unnitel
    -0.59
    thalam
    -0.59
    ocardial
    -0.58
    HasColumnName
    -0.58
    ########.
    -0.57
    POSITIVE LOGITS
     democracy
    1.94
     democratic
    1.70
    democracy
    1.64
     Democracy
    1.61
    Democracy
    1.61
    democratic
    1.55
     democracies
    1.46
     democrat
    1.40
     demokra
    1.29
     democrá
    1.27
    Act Density 0.070%

    No Known Activations