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

    Neuronpedia

    INDEX
    Explanations

    markers for the beginning of new sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.86
    expandindo
    -0.81
    +#+
    -0.73
    存于互联网档案馆
    -0.72
     flexing
    -0.72
     profilo
    -0.71
    >−
    -0.70
     copiar
    -0.70
    帖最后由
    -0.70
    Diwedd
    -0.69
    POSITIVE LOGITS
     gummies
    2.67
     Gummies
    2.22
     gummy
    1.19
     pills
    0.73
     Audiodateien
    0.62
     candies
    0.62
     Gummi
    0.59
     tickets
    0.58
     pill
    0.58
     gum
    0.58
    Act Density 0.029%

    No Known Activations