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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers indicating position, particularly in a numerical sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to ordinal numbers and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cra
    -0.74
    uploads
    -0.68
    infeld
    -0.68
    cks
    -0.63
    IDA
    -0.63
    bda
    -0.62
    archives
    -0.62
     Hendricks
    -0.61
    ++++++++++++++++
    -0.61
    bia
    -0.60
    POSITIVE LOGITS
     inning
    1.15
    ousand
    1.06
    irty
    1.01
    teenth
    0.99
     century
    0.98
    ousands
    0.94
     percentile
    0.90
     generation
    0.90
    ieth
    0.88
     iteration
    0.87
    Act Density 0.054%

    No Known Activations