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

    Neuronpedia

    INDEX
    Explanations

    references to mechanisms and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.32
     two
    -0.31
     bislang
    -0.31
     leading
    -0.30
     recent
    -0.30
     进行
    -0.30
     대해
    -0.29
     Semoga
    -0.28
     Veja
    -0.28
    Lähteet
    -0.28
    POSITIVE LOGITS
    AddTagHelper
    0.77
     mechanism
    0.73
     Lobby
    0.72
    ContentAlignment
    0.70
    <unused14>
    0.69
    <pad>
    0.69
    <unused43>
    0.69
     メンテナ
    0.68
    <unused79>
    0.68
    <unused74>
    0.68
    Act Density 0.247%

    No Known Activations