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

    Neuronpedia

    INDEX
    Explanations

    references to emotional responses and human interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibre
    -0.16
    ãĥªãĥ¼ãĤº
    -0.15
    ulp
    -0.14
    eut
    -0.14
    ulpt
    -0.14
    teri
    -0.14
    .gstatic
    -0.13
     aVar
    -0.13
    OffsetTable
    -0.13
    ekt
    -0.13
    POSITIVE LOGITS
    ´Ŀ
    0.17
    amage
    0.14
    oss
    0.14
     Heg
    0.14
    ãĤ¦ãĤ¹
    0.13
    bone
    0.13
     bò
    0.12
    æĮĻ
    0.12
     Gilles
    0.12
    708
    0.12
    Act Density 0.286%

    No Known Activations