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

    Neuronpedia

    INDEX
    Explanations

    references to books and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.83
     reader
    -0.71
     lecteur
    -0.66
    Reading
    -0.64
    Tikang
    -0.62
     Reading
    -0.61
    reading
    -0.61
     Escrit
    -0.60
     leitor
    -0.60
    󠁣
    -0.59
    POSITIVE LOGITS
     books
    0.78
     children
    0.69
     childrens
    0.69
     nonfiction
    0.63
     book
    0.60
     textbooks
    0.60
     popular
    0.59
     best
    0.59
     boks
    0.56
     biography
    0.56
    Act Density 0.241%

    No Known Activations