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

    Neuronpedia

    INDEX
    Explanations

    legal phrases and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issing
    -0.20
    zung
    -0.16
    monds
    -0.15
    668
    -0.14
     neutral
    -0.14
    contro
    -0.14
    uple
    -0.14
    ÙĪاء
    -0.14
     Neutral
    -0.14
    Neutral
    -0.14
    POSITIVE LOGITS
     Bak
    0.15
    EOS
    0.15
    icers
    0.15
    Ïģθ
    0.15
    γα
    0.14
    á»Ŀ
    0.14
    anon
    0.14
    ovÄĽ
    0.14
     Venom
    0.13
    iesta
    0.13
    Act Density 0.048%

    No Known Activations