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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures indicating sets or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     larmes
    -0.63
     atletas
    -0.61
     alguno
    -0.61
     inconvénients
    -0.60
     militaires
    -0.60
     foramen
    -0.57
     déchir
    -0.57
     atleta
    -0.57
     saira
    -0.57
     ennemis
    -0.57
    POSITIVE LOGITS
    )";
    0.97
    =[];
    0.93
    arraycopy
    0.92
    ...");
    0.88
    一系列
    0.86
    `,
    0.85
    \"");
    0.85
    %;
    0.84
    )");
    0.82
     &[
    0.82
    Act Density 0.346%

    No Known Activations