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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.70
    AutoScaleMode
    -0.70
    rxjs
    -0.61
    ಾನ
    -0.61
    تقاوى
    -0.61
    oski
    -0.60
    uing
    -0.60
    그는
    -0.59
    KindOfClass
    -0.59
     autorytatywna
    -0.58
    POSITIVE LOGITS
    ↵↵
    0.97
    )})
    0.92
    }});
    0.90
    }})
    0.87
    </tr>
    0.86
     الحره
    0.85
    )])
    0.84
    ]})
    0.83
    )))));
    0.83
    ])));
    0.81
    Act Density 0.318%

    No Known Activations