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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social and cultural dynamics, especially those involving power, control, and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elog
    -0.18
    plen
    -0.17
     lip
    -0.14
    .epam
    -0.14
    ãĥªãĤ¢
    -0.14
    lip
    -0.14
    .TestTools
    -0.14
    uards
    -0.13
     lep
    -0.13
     Premium
    -0.13
    POSITIVE LOGITS
    zeit
    0.16
    igor
    0.16
    orm
    0.15
    vably
    0.15
    Sizer
    0.15
    ivy
    0.15
    ä¹Ī
    0.14
     nbytes
    0.14
    tal
    0.14
     frü
    0.14
    Act Density 0.029%

    No Known Activations