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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "have" in various tenses and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.74
     ſche
    -0.73
     Eocene
    -0.72
     goofy
    -0.71
     Monfieur
    -0.70
     houſe
    -0.70
     betweenstory
    -0.70
     Jefus
    -0.68
     fevere
    -0.68
     Producción
    -0.67
    POSITIVE LOGITS
     been
    1.12
     has
    1.08
     have
    1.06
     telah
    0.90
     had
    0.88
     recently
    0.82
     đã
    0.79
     dàng
    0.76
     Has
    0.70
     never
    0.70
    Act Density 0.342%

    No Known Activations