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

    Neuronpedia

    INDEX
    Explanations

    mathematical propositions and references to theorems and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchar
    -0.16
     Gand
    -0.14
    rome
    -0.14
    Dummy
    -0.14
     flip
    -0.14
    .DEFINE
    -0.14
    razier
    -0.13
    ÏĨÏħ
    -0.13
    ãĥ¼ãĥĦ
    -0.13
    ãģĿãģĹãģ¦
    -0.13
    POSITIVE LOGITS
    oin
    0.18
    ftime
    0.16
     Erick
    0.14
    961
    0.14
    еÑģп
    0.14
    elly
    0.14
    ¯u
    0.14
    pane
    0.14
     promot
    0.14
    vr
    0.13
    Act Density 0.082%

    No Known Activations