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

    Neuronpedia

    INDEX
    Explanations

    HTML/XML tags and formatting-related tokens

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    LT
    -0.99
    amp
    -0.79
     amp
    -0.75
     LT
    -0.74
     lt
    -0.71
    Amp
    -0.69
     وتسجيلات
    -0.67
     Amp
    -0.63
    انجليز
    -0.60
    AMP
    -0.56
    POSITIVE LOGITS
    }></
    0.62
    >%
    0.62
    >",
    0.61
    })
    0.59
    }>
    0.59
    }))
    0.59
    >
    0.57
    )</
    0.57
    äfte
    0.57
    __':
    0.57
    Act Density 0.004%

    No Known Activations