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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     was
    -1.01
     had
    -0.89
     seemed
    -0.88
     became
    -0.87
    seemed
    -0.86
     pouvait
    -0.83
     hadn
    -0.82
     were
    -0.81
     knew
    -0.81
    was
    -0.81
    POSITIVE LOGITS
    ίναι
    0.65
     awaits
    0.64
     немає
    0.63
     Есть
    0.62
     sahiptir
    0.61
    kazuje
    0.60
     existem
    0.59
     υπάρχει
    0.59
     existen
    0.59
     вчера
    0.57
    Act Density 0.435%

    No Known Activations