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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ab
    -0.56
    。
    -0.55
     Bre
    -0.53
     。
    -0.53
     En
    -0.52
    》。
    -0.52
    ."
    -0.52
     Che
    -0.52
     Kim
    -0.51
    tonode
    -0.51
    POSITIVE LOGITS
     Majefty
    0.79
     fubject
    0.78
     خارجية
    0.74
     Paglinawan
    0.72
     pleaſure
    0.71
     tecnici
    0.69
     EconPapers
    0.67
    mybatisplus
    0.67
     تانيه
    0.67
     كومونز
    0.66
    Act Density 0.325%

    No Known Activations