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

    Neuronpedia

    INDEX
    Explanations

    code-related elements within content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.96
    ftant
    -0.91
     Lath
    -0.88
    ••••
    -0.87
     Hemis
    -0.86
     Koz
    -0.86
     testData
    -0.84
    ftance
    -0.81
     لينك
    -0.80
     Jefus
    -0.80
    POSITIVE LOGITS
    </code>
    2.08
    </i>
    1.40
    </em>
    1.34
    </s>
    1.33
    })));
    1.23
    }`
    1.22
    </u>
    1.21
    )`
    1.20
    </sup>
    1.16
    })`
    1.11
    Act Density 0.155%

    No Known Activations