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

    Neuronpedia

    INDEX
    Explanations

    mathematical or technical references and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.83
    parsedMessage
    -0.75
    RegressionTest
    -0.73
    <unused43>
    -0.69
    <unused41>
    -0.69
    <unused8>
    -0.68
    <unused51>
    -0.68
    <unused74>
    -0.68
    <unused28>
    -0.68
    <unused23>
    -0.68
    POSITIVE LOGITS
    LEGGI
    0.38
     labeled
    0.29
     corresponding
    0.28
    
    0.28
    t
    0.28
     which
    0.28
     desac
    0.27
    Kind
    0.27
     applied
    0.27
    );
    0.27
    Act Density 0.000%

    No Known Activations