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

    Neuronpedia

    INDEX
    Explanations

    numerical representations or mentions of age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.87
     Orrell
    -0.83
    IBinder
    -0.74
    </strong>
    -0.69
    /
    -0.66
    )
    -0.64
    er
    -0.63
     car
    -0.62
     def
    -0.59
     “
    -0.59
    POSITIVE LOGITS
     eighty
    2.10
     seventy
    2.08
     sixty
    2.04
     fifty
    2.00
     ninety
    2.00
     forty
    1.98
     thirty
    1.97
     twenty
    1.95
    twenty
    1.80
    forty
    1.76
    Act Density 0.164%

    No Known Activations