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

    Neuronpedia

    INDEX
    Explanations

    code-related punctuation and syntax elements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affaires
    -0.58
     romain
    -0.57
     démocr
    -0.57
     själ
    -0.54
     Aton
    -0.54
     virš
    -0.54
     Haan
    -0.53
     nationaux
    -0.53
     écoute
    -0.52
     sine
    -0.52
    POSITIVE LOGITS
    ]");
    3.40
    ']);
    3.33
    }");
    3.28
    "]);
    3.28
    "];
    3.27
    ]');
    3.25
    }`);
    3.20
    `);
    3.20
    '];
    3.18
    >');
    3.17
    Act Density 0.200%

    No Known Activations