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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their corresponding forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chriſt
    -1.08
     Monfieur
    -1.05
     purpoſe
    -0.95
     ſeveral
    -0.90
     Jefus
    -0.90
     Chriftian
    -0.89
     greateſt
    -0.87
     houſe
    -0.86
     Wicidata
    -0.86
     fevere
    -0.86
    POSITIVE LOGITS
     be
    0.66
     kunne
    0.63
     EconPapers
    0.63
     Ha
    0.61
    ',\
    0.61
    )$_
    0.61
     נ
    0.60
     F
    0.59
    '))
    0.59
     ي
    0.58
    Act Density 0.043%

    No Known Activations