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

    Neuronpedia

    INDEX
    Explanations

    instances of examples being provided or referenced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >");
    -0.89
    '),
    -0.77
    "]);
    -0.76
    ()))
    -0.73
    '];
    -0.73
    }');
    -0.73
    '))
    -0.72
     }</
    -0.72
    ...");
    -0.72
     חיצוניים
    -0.72
    POSITIVE LOGITS
    Например
    0.78
     Например
    0.70
    например
    0.68
     example
    0.67
     eg
    0.65
    Eg
    0.61
     Eg
    0.60
     например
    0.57
     Like
    0.56
     např
    0.54
    Act Density 0.295%

    No Known Activations