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

    Neuronpedia

    INDEX
    Explanations

    references to literary works or scholarship related to literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sst
    -0.16
    imiz
    -0.15
    agon
    -0.15
     kaz
    -0.15
    orth
    -0.14
    Å¡ak
    -0.14
    .yang
    -0.14
    ¡
    -0.14
    æŁ³
    -0.14
     kne
    -0.14
    POSITIVE LOGITS
    iminal
    0.19
    /devices
    0.16
    uem
    0.16
    prm
    0.16
     Abbott
    0.15
    ãĥ¼ãĥĦ
    0.14
    747
    0.14
    odos
    0.14
    urgical
    0.14
    trl
    0.14
    Act Density 0.005%

    No Known Activations