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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating purpose or function

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

    introducing purpose or reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.69
     EconPapers
    -0.69
    istoitu
    -0.67
    expandindo
    -0.59
    StoreMessageInfo
    -0.58
    出版年
    -0.56
     iprot
    -0.56
     transfieras
    -0.54
     kaarangay
    -0.53
    ValueStyle
    -0.53
    POSITIVE LOGITS
     to
    0.89
     чтобы
    0.76
    เพื่อ
    0.59
    Чтобы
    0.57
     afin
    0.57
     để
    0.57
    为了
    0.53
     כדי
    0.51
     щоб
    0.49
     upang
    0.48
    Act Density 0.085%

    No Known Activations