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

    Neuronpedia

    INDEX
    Explanations

    references to political events or parties, particularly those involving elections and coalition formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     republi
    -0.45
    εια
    -0.43
     Xerox
    -0.41
    diana
    -0.41
    нор
    -0.40
     Avic
    -0.40
     Materia
    -0.40
     hum
    -0.39
     Kenobi
    -0.39
     Heuer
    -0.39
    POSITIVE LOGITS
     party
    0.94
     parties
    0.84
     coalition
    0.83
     Movement
    0.83
     alliance
    0.82
     movement
    0.80
     faction
    0.79
    TypedDataSet
    0.79
     partidos
    0.77
    oneofs
    0.77
    Act Density 0.317%

    No Known Activations