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

    Neuronpedia

    INDEX
    Explanations

    sections or headings in documents, particularly focusing on structured elements like agreements and research methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whatnot
    -0.65
    Кстати
    -0.63
     entanto
    -0.62
    ailleurs
    -0.61
     meanwhile
    -0.61
    равда
    -0.61
     anyway
    -0.59
     Whats
    -0.59
     moreover
    -0.59
    +#+#
    -0.58
    POSITIVE LOGITS
     skolan
    0.58
     klubben
    0.56
     compé
    0.53
     guerres
    0.52
    ंदीखरीदारी
    0.52
     The
    0.52
    The
    0.51
     souffrance
    0.51
     רבים
    0.51
    psack
    0.51
    Act Density 0.411%

    No Known Activations