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

    Neuronpedia

    INDEX
    Explanations

    test assertions and results in code snippets, particularly focusing on equality checks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     propOrder
    -0.73
    niająca
    -0.72
    帖最后由
    -0.67
     архивлан
    -0.65
    RepeatedField
    -0.65
    crypted
    -0.64
     betweenstory
    -0.64
    titleMargin
    -0.63
    webElementGuid
    -0.61
    دانشنامهٔ
    -0.61
    POSITIVE LOGITS
    Races
    0.62
    Enllaces
    0.54
    FloatField
    0.52
    banco
    0.50
    ('|
    0.50
     CURIAM
    0.49
    ('\\
    0.49
    parsedMessage
    0.47
     Races
    0.46
     contextLoads
    0.46
    Act Density 0.009%

    No Known Activations