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

    Neuronpedia

    INDEX
    Explanations

    code formatting or code-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licet
    -0.84
     Koz
    -0.83
    ftant
    -0.81
     Efq
    -0.80
    ^(@)
    -0.80
    Lom
    -0.79
    ••••
    -0.79
    SLIDE
    -0.78
     们
    -0.78
    ghijklmnop
    -0.76
    POSITIVE LOGITS
    </code>
    1.79
    </blockquote>
    1.18
    "}")
    1.08
    </i>
    1.06
    </th>
    1.03
    )`
    1.02
    }`
    1.02
    })));
    1.01
    `,
    0.95
    </em>
    0.95
    Act Density 0.282%

    No Known Activations