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

    Neuronpedia

    INDEX
    Explanations

    data structure closing brackets or semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing brackets and semicolons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused41>
    -1.28
    <unused14>
    -1.27
    <unused52>
    -1.27
    <unused74>
    -1.27
    <unused17>
    -1.27
    <unused3>
    -1.27
    <unused79>
    -1.27
    <unused68>
    -1.27
    <unused28>
    -1.27
    <pad>
    -1.27
    POSITIVE LOGITS
    ];
    0.78
    );
    0.69
    ;
    0.69
    };
    0.66
    ();
    0.64
    '];
    0.63
    ';
    0.59
    ');
    0.59
    })));
    0.59
    ");
    0.57
    Act Density 0.009%

    No Known Activations