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

    Neuronpedia

    INDEX
    Explanations

    references to "prime" or "primed" objects or concepts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']))
    -0.94
    "]=
    -0.81
    "}>
    -0.80
    '}>
    -0.78
    "],
    -0.77
    \">\
    -0.76
    )<\
    -0.76
    }}]{
    -0.75
     )}
    -0.74
    }>
    -0.74
    POSITIVE LOGITS
    prime
    2.47
     prime
    1.80
    Prime
    1.67
     Prime
    1.58
    PRIME
    1.58
     PRIME
    1.48
     primes
    1.35
    primes
    1.26
    ′
    1.13
    Primes
    1.09
    Act Density 0.100%

    No Known Activations