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

    Neuronpedia

    INDEX
    Explanations

    instances of line breaks or formatting markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nde
    -0.66
     cá
    -0.64
     trial
    -0.64
    zz
    -0.64
     Galbraith
    -0.64
     school
    -0.64
     leg
    -0.64
    dal
    -0.62
     dig
    -0.62
    AsUp
    -0.61
    POSITIVE LOGITS
     \\
    1.27
    ")]
    1.09
    ])));
    1.02
     发表于
    1.00
    }")]
    0.98
    </h5>
    0.96
    </td>
    0.96
    ])))
    0.96
    ]));
    0.96
    WriteBarrier
    0.96
    Act Density 0.005%

    No Known Activations