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

    Neuronpedia

    INDEX
    Explanations

    identifiers and markers of social interaction or community membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥ãĥ¼
    -0.22
     اÙĦخاÙħسة
    -0.15
    iske
    -0.15
    etas
    -0.15
    466
    -0.15
    ingles
    -0.15
    .snap
    -0.15
     crack
    -0.15
     fours
    -0.14
    /commons
    -0.14
    POSITIVE LOGITS
    za
    0.17
    eless
    0.16
    adr
    0.15
     Hillary
    0.15
    elize
    0.15
    Äįan
    0.14
    andro
    0.14
    amu
    0.14
    à¸Ĺร
    0.14
    ulas
    0.14
    Act Density 0.027%

    No Known Activations