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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time or duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouf
    -0.88
    oper
    -0.79
    oppers
    -0.78
    iola
    -0.75
    ariat
    -0.75
    atively
    -0.72
    amy
    -0.71
    organ
    -0.71
    abet
    -0.71
    ologue
    -0.69
    POSITIVE LOGITS
    terness
    1.13
     awhile
    1.11
     Ago
    0.95
    inventoryQuantity
    0.86
    catentry
    0.83
     awa
    0.81
     ago
    0.80
    ãĤ¼ãĤ¦ãĤ¹
    0.77
    EStream
    0.76
    tesy
    0.73
    Act Density 0.006%

    No Known Activations