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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal aspirations and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anders
    -0.08
    ander
    -0.08
    kr
    -0.07
    olio
    -0.07
    plib
    -0.07
    æµľ
    -0.07
    uien
    -0.07
    inish
    -0.07
    .bundle
    -0.07
    neum
    -0.07
    POSITIVE LOGITS
     prime
    0.13
     peak
    0.12
     Prime
    0.10
     age
    0.09
     primes
    0.09
    Peak
    0.09
    peak
    0.09
    Prime
    0.09
     Peak
    0.09
    prime
    0.08
    Act Density 0.037%

    No Known Activations