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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     someone
    -0.18
    someone
    -0.18
    ä¸Ģ个人
    -0.17
     Someone
    -0.17
     somebody
    -0.17
    اÙĨÙĬØ©
    -0.16
    ozem
    -0.16
     alguien
    -0.15
    uger
    -0.15
    Someone
    -0.15
    POSITIVE LOGITS
     quite
    0.30
     Quite
    0.25
    quite
    0.24
     such
    0.21
     SUCH
    0.20
     an
    0.16
    Quite
    0.16
    olas
    0.15
     amore
    0.14
    åIJĽ
    0.14
    Act Density 0.397%

    No Known Activations