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

    Neuronpedia

    INDEX
    Explanations

    references to specific business-related terms or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anco
    -0.16
    ιÏİ
    -0.15
    onis
    -0.15
    dess
    -0.15
    atty
    -0.14
    acht
    -0.14
     trình
    -0.14
    диÑı
    -0.13
    /navbar
    -0.13
     Ty
    -0.13
    POSITIVE LOGITS
    wand
    0.18
    ils
    0.15
    ernes
    0.15
    apus
    0.14
    .Guna
    0.14
    aus
    0.14
    oms
    0.14
    ienes
    0.14
    «a
    0.14
     unstable
    0.14
    Act Density 0.008%

    No Known Activations