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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns such as synchronization codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hindsight
    -0.65
    glers
    -0.62
     comprom
    -0.52
    raq
    -0.52
     ultras
    -0.52
    itaire
    -0.51
     inev
    -0.49
    onite
    -0.49
     icing
    -0.48
     accelerator
    -0.48
    POSITIVE LOGITS
    usercontent
    0.56
    SourceFile
    0.54
    é¾įåĸļ士
    0.49
     CrossRef
    0.49
     attRot
    0.48
    #
    0.48
     ãĥ
    0.47
    cloud
    0.47
    Catal
    0.47
    aiden
    0.47
    Act Density 0.496%

    No Known Activations