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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation that express contrast or continuation in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    but Peach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsVisible
    -0.49
    IFICATE
    -0.48
    läge
    -0.47
    culus
    -0.47
    itemID
    -0.46
    mbic
    -0.45
     investi
    -0.45
    age
    -0.45
     arras
    -0.45
    endregion
    -0.44
    POSITIVE LOGITS
    但
    1.53
     但
    1.28
    但她
    1.09
    但他
    1.08
    但在
    1.03
    但我
    1.00
     nhưng
    0.96
    But
    0.88
     But
    0.83
    但这
    0.82
    Act Density 0.003%

    No Known Activations