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

    Neuronpedia

    INDEX
    Explanations

    terms related to the training and architecture of neural networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CodeAttribute
    -0.45
    IndentedString
    -0.44
    SequentialGroup
    -0.43
    orianCalendar
    -0.41
    endphp
    -0.40
     yyr
    -0.40
    scalatest
    -0.38
    withIdentifier
    -0.38
    ByExample
    -0.37
    SharedCtor
    -0.37
    POSITIVE LOGITS
     input
    3.67
     Input
    3.39
     inputs
    3.20
    input
    3.11
    Input
    3.11
     INPUT
    3.02
     Inputs
    2.92
    INPUT
    2.81
    输入
    2.66
    inputs
    2.56
    Act Density 1.031%

    No Known Activations