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

    Neuronpedia

    INDEX
    Explanations

    technical formatting or structure in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     militaires
    -0.86
     étoit
    -0.78
     célè
    -0.78
     spéciaux
    -0.77
     Wikimedijinoj
    -0.77
    :✨
    -0.76
     ModelExpression
    -0.76
    principalColumn
    -0.74
    клопе
    -0.73
     croire
    -0.73
    POSITIVE LOGITS
    2
    0.60
    1
    0.59
    4
    0.56
    0
    0.54
     
    0.54
    3
    0.54
    9
    0.53
    5
    0.53
    7
    0.49
    8
    0.49
    Act Density 0.547%

    No Known Activations