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

    Neuronpedia

    INDEX
    Explanations

    references to characters and entities involved in dialogues or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.69
    AntiForgeryToken
    -0.66
     дописавши
    -0.64
    EndContext
    -0.57
    請繼續往下閱讀
    -0.57
     <=",
    -0.55
     queſta
    -0.54
     autorytatywna
    -0.53
     Audiodateien
    -0.53
     ModelExpression
    -0.52
    POSITIVE LOGITS
     why
    0.34
    Nolan
    0.32
    Alec
    0.29
    got
    0.29
    hinh
    0.29
     combien
    0.28
     Autor
    0.28
     pourquoi
    0.28
     relevance
    0.28
    OrFail
    0.28
    Act Density 0.659%

    No Known Activations