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

    Neuronpedia

    INDEX
    Explanations

    references to the pronoun "you" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Referencie
    -0.81
    Portale
    -0.73
    Portail
    -0.62
     pleaſure
    -0.61
    PreferredItem
    -0.60
     OFDb
    -0.57
     tranſ
    -0.51
     Monfieur
    -0.51
     Chriftian
    -0.51
     Jefus
    -0.49
    POSITIVE LOGITS
     may
    0.71
     should
    0.68
     probably
    0.67
     might
    0.66
     generally
    0.66
     devrez
    0.60
     voud
    0.59
     pouvez
    0.58
     bör
    0.58
     umumnya
    0.58
    Act Density 0.136%

    No Known Activations