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

    Neuronpedia

    INDEX
    Explanations

    instances of political corruption and related accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAttribute
    -0.66
     almofada
    -0.63
     quaisquer
    -0.63
     MainAxisSize
    -0.62
     unicórnio
    -0.60
     traseira
    -0.58
    期刊论文
    -0.57
     pistolet
    -0.56
     borboleta
    -0.55
     Libros
    -0.55
    POSITIVE LOGITS
    Referências
    0.56
    scriptcase
    0.54
     Brazilian
    0.44
     brazilian
    0.43
    expandindo
    0.43
    Brazilian
    0.39
    nmgp
    0.37
     portug
    0.36
     brasili
    0.35
    Brazil
    0.35
    Act Density 0.573%

    No Known Activations