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

    Neuronpedia

    INDEX
    Explanations

    questions and requests for clarification or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.02
     myſelf
    -0.97
     Theſe
    -0.96
     photolibrary
    -0.95
     وتسجيلات
    -0.95
     whoſe
    -0.95
     Reſ
    -0.94
     Houſe
    -0.94
     Monfieur
    -0.94
     leaſt
    -0.93
    POSITIVE LOGITS
     суть
    0.61
    :
    0.55
     
    0.54
     :
    0.50
     Specifically
    0.49
    具体
    0.49
    如下
    0.47
     Hintergrund
    0.47
     polega
    0.47
     (
    0.47
    Act Density 0.481%

    No Known Activations