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

    Neuronpedia

    INDEX
    Explanations

    closing brackets across various types of code or structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rest
    -0.77
     D
    -0.64
     Gra
    -0.63
     hu
    -0.62
     meg
    -0.62
     kinh
    -0.61
     van
    -0.59
    <sup>
    -0.59
     Le
    -0.59
    สม
    -0.59
    POSITIVE LOGITS
    "}
    2.00
    )}
    1.99
    '}
    1.91
    ]}
    1.87
    ))}
    1.86
    }
    1.86
    ).}
    1.80
    .)}
    1.78
    "]}
    1.78
    })}
    1.76
    Act Density 0.382%

    No Known Activations