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

    Neuronpedia

    INDEX
    Explanations

    references to social groups or relationships involving shared identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    standers
    -0.49
     superiori
    -0.48
    stander
    -0.48
    Ikus
    -0.48
     legais
    -0.47
    warma
    -0.46
    abetes
    -0.46
     Twins
    -0.46
    Czytaj
    -0.46
     للمعارف
    -0.45
    POSITIVE LOGITS
     fellow
    0.58
    一名
    0.56
    是一位
    0.52
    一位
    0.51
     นัก
    0.50
    那位
    0.49
    这位
    0.48
     createState
    0.47
     veteran
    0.47
    นัก
    0.47
    Act Density 0.703%

    No Known Activations