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

    Neuronpedia

    INDEX
    Explanations

    relative clauses and pronouns referring to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desorption
    -0.65
     Summa
    -0.64
    Alte
    -0.59
     lavado
    -0.58
     alberi
    -0.56
     spher
    -0.56
     Appreciate
    -0.56
     NEO
    -0.56
     blest
    -0.56
     olev
    -0.55
    POSITIVE LOGITS
     who
    1.15
     []:
    1.02
     która
    0.84
    `;
    0.83
    примеча
    0.82
    )";
    0.82
    osoever
    0.82
    %
    0.81
     quien
    0.80
     والذي
    0.80
    Act Density 0.527%

    No Known Activations