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

    Neuronpedia

    INDEX
    Explanations

    issues related to programming errors and exceptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TagMode
    -0.94
    Portale
    -0.91
     Мексичка
    -0.90
    BufferException
    -0.90
    GraphicsUnit
    -0.87
    ]';
    -0.85
     contextLoads
    -0.85
    ]";
    -0.82
     AppColors
    -0.82
    发表于
    -0.81
    POSITIVE LOGITS
     you
    0.93
     your
    0.84
     I
    0.83
     something
    0.78
     guys
    0.75
     somebody
    0.73
     really
    0.71
     someone
    0.71
     pretty
    0.69
     nice
    0.69
    Act Density 8.793%

    No Known Activations