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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "prime" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prime followed by modifying noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.58
     Throwable
    -0.49
    transQ
    -0.48
     throwable
    -0.48
    tattoo
    -0.47
    lioz
    -0.47
     Tattoo
    -0.47
    Tattoo
    -0.46
    Taller
    -0.45
     updateUser
    -0.44
    POSITIVE LOGITS
     Prime
    1.58
    Prime
    1.50
     prime
    1.48
     PRIME
    1.37
    PRIME
    1.23
    prime
    1.16
     primes
    0.95
    isPrime
    0.84
     primed
    0.84
     priming
    0.81
    Act Density 0.012%

    No Known Activations