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

    Neuronpedia

    INDEX
    Explanations

    negative or contrasting sentiments in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eb
    -0.17
    ัà¸ģ
    -0.15
    elden
    -0.15
     WCHAR
    -0.15
    .wr
    -0.15
    eldon
    -0.14
    ød
    -0.14
    EB
    -0.14
    ennen
    -0.13
    forums
    -0.13
    POSITIVE LOGITS
    åĬ¨çĶŁæĪIJ
    0.15
    ãģ£ãģı
    0.15
    elsen
    0.15
    HING
    0.14
    aylight
    0.14
    ritz
    0.14
     DataView
    0.14
    ensus
    0.13
    xbe
    0.13
     newInstance
    0.13
    Act Density 0.300%

    No Known Activations