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

    Neuronpedia

    INDEX
    Explanations

    HTML tags or formatting elements indicating emphasis like bold and italic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÁG
    -0.68
    xnn
    -0.68
     meg
    -0.64
     التن
    -0.62
    存于互联网档案馆
    -0.61
    ſion
    -0.59
    runk
    -0.59
    DEPART
    -0.58
     Witten
    -0.58
     Chau
    -0.58
    POSITIVE LOGITS
    estacks
    0.87
    )])
    0.78
    </em>
    0.77
    }());
    0.75
    }}],
    0.74
    </code>
    0.74
    }])
    0.71
    </sup>
    0.70
    </sub>
    0.70
    ]))
    0.70
    Act Density 0.069%

    No Known Activations