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

    Neuronpedia

    INDEX
    Explanations

    temporal references or phrases indicating specific points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Referencies
    -0.88
     propOrder
    -0.71
    yntaxException
    -0.66
     Theſe
    -0.62
    ]<<"
    -0.61
    SharedCtor
    -0.61
    StreetMap
    -0.60
    #+#
    -0.59
    principalColumn
    -0.59
     bezeichneter
    -0.59
    POSITIVE LOGITS
     damals
    0.94
     then
    0.87
    当时的
    0.87
     damaligen
    0.86
    当时
    0.85
     entonces
    0.82
    當時
    0.79
    那时
    0.79
     тогда
    0.77
    その時
    0.76
    Act Density 0.153%

    No Known Activations