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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers indicating a position in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to ordinal numbers, particularly 'fifth' and 'sixth'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.77
    cks
    -0.75
    bda
    -0.73
    ++++++++++++++++
    -0.70
    VE
    -0.70
    facts
    -0.67
    uploads
    -0.66
    NUM
    -0.66
    pees
    -0.66
    infeld
    -0.65
    POSITIVE LOGITS
     inning
    1.23
    teenth
    0.96
    irty
    0.95
     quarter
    0.89
     century
    0.89
     iteration
    0.88
    ousand
    0.88
    ieth
    0.88
    ulhu
    0.87
     installment
    0.86
    Act Density 0.034%

    No Known Activations