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

    Neuronpedia

    INDEX
    Explanations

    terms associated with political manipulation and societal criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loisirs
    -0.60
     vélos
    -0.58
     cérami
    -0.51
     nasional
    -0.50
     autorités
    -0.50
     congrès
    -0.49
     juges
    -0.49
     églises
    -0.49
     câbles
    -0.48
    nál
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.79
     تضيفلها
    0.70
     rigueur
    0.67
    Personensuche
    0.67
     antics
    0.66
     infamous
    0.66
     dreams
    0.65
     extravag
    0.65
     الرياضيه
    0.65
     cherchés
    0.64
    Act Density 6.339%

    No Known Activations