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

    Neuronpedia

    INDEX
    Explanations

    specific numerical codes, possibly related to locations or events

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences, particularly those that resemble addresses or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.80
    neys
    -0.78
    icial
    -0.72
    sterdam
    -0.68
    amount
    -0.68
    ulet
    -0.65
    lings
    -0.65
    ston
    -0.62
    lined
    -0.61
    steen
    -0.61
    POSITIVE LOGITS
     partName
    0.98
    603
    0.83
    703
    0.82
    646
    0.81
    806
    0.80
    608
    0.79
    807
    0.78
    605
    0.77
    409
    0.77
    201
    0.75
    Act Density 0.051%

    No Known Activations