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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and references to the user

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.97
     للاسماء
    -0.84
    MessageOf
    -0.79
     Мексичка
    -0.77
    actéristique
    -0.76
     Efq
    -0.73
    帖最后由
    -0.71
    :✨
    -0.71
     defaultstate
    -0.69
    spreis
    -0.69
    POSITIVE LOGITS
    </h1>
    0.66
    </h2>
    0.54
    ’).
    0.51
    </sub>
    0.50
    ').
    0.50
    ↵↵↵↵↵
    0.49
     متعلقه
    0.48
    )}.
    0.48
     }).
    0.47
    ]").
    0.47
    Act Density 0.012%

    No Known Activations