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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" and variations that indicate collective experience or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kami
    -0.90
     our
    -0.84
    我們的
    -0.82
     ourselves
    -0.79
     الحره
    -0.75
     שלנו
    -0.73
    我们是
    -0.72
     ours
    -0.72
    我们的
    -0.72
    我们
    -0.72
    POSITIVE LOGITS
    ########.
    0.85
     witnessing
    0.65
     witnessed
    0.61
     all
    0.60
     allemaal
    0.58
    Personendaten
    0.57
     witness
    0.56
     seeing
    0.55
     hear
    0.54
    出版年
    0.52
    Act Density 0.183%

    No Known Activations