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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to performance and revenue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PSU
    -0.15
     grav
    -0.15
    iaux
    -0.14
     afs
    -0.14
    ifetime
    -0.14
    alous
    -0.14
    lifetime
    -0.14
     åĤ
    -0.13
     Chamber
    -0.13
    adder
    -0.13
    POSITIVE LOGITS
    antasy
    0.17
    лик
    0.15
    ovel
    0.15
     Bread
    0.15
    ì°¨
    0.14
     syndrome
    0.14
    ë§Īëĭ¤
    0.14
    _updates
    0.14
     updates
    0.14
     bread
    0.14
    Act Density 0.150%

    No Known Activations