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

    Neuronpedia

    INDEX
    Explanations

    pronouns and personal identity references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     he
    -0.82
     himself
    -0.73
     him
    -0.68
     his
    -0.66
     él
    -0.62
    他才
    -0.56
     dirinya
    -0.55
    He
    -0.55
    他也
    -0.55
    他
    -0.55
    POSITIVE LOGITS
     صوتيه
    1.08
    featureID
    0.89
     للمعارف
    0.88
    endphp
    0.83
    ynb
    0.81
    fjspx
    0.79
    tagHelperRunner
    0.77
    脚注の使い方
    0.76
     незавершена
    0.75
    ChildScrollView
    0.75
    Act Density 0.402%

    No Known Activations