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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "visited" or tracking visitation status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    places visited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.57
     pleaſure
    -0.50
     purpoſe
    -0.48
    empereur
    -0.47
     enggak
    -0.46
     slutt
    -0.46
     olvides
    -0.45
     dabar
    -0.45
     strøm
    -0.43
     meille
    -0.43
    POSITIVE LOGITS
    visited
    1.77
     visited
    1.73
     Visited
    1.70
    Visited
    1.52
     frequented
    0.97
     visitó
    0.91
     traversed
    0.90
     toured
    0.88
     revisited
    0.86
     travelled
    0.85
    Act Density 0.004%

    No Known Activations