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

    Neuronpedia

    INDEX
    Explanations

    numbers representing age

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable age-related numbers or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ller
    -0.77
    Bank
    -0.76
    BOOK
    -0.74
    Helper
    -0.73
    TPP
    -0.68
    HC
    -0.67
    Guard
    -0.66
    liv
    -0.65
    LCS
    -0.64
    Climate
    -0.64
    POSITIVE LOGITS
     thousand
    1.25
    eenth
    1.14
     hundred
    1.06
    teenth
    0.99
    ieth
    0.90
    uously
    0.88
     thous
    0.88
     Thousand
    0.88
    fold
    0.85
    uous
    0.85
    Act Density 0.020%

    No Known Activations