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

    Neuronpedia

    INDEX
    Explanations

    words related to subcategories or groups within a larger category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikispecies
    -0.91
     Siren
    -0.90
     Мексичка
    -0.90
    Fordítás
    -0.88
     ainfi
    -0.85
    kepada
    -0.84
    Cordialement
    -0.82
     Conservancy
    -0.82
    polation
    -0.82
    ✨:
    -0.81
    POSITIVE LOGITS
    Pro
    1.21
    o
    1.15
    a
    1.11
    pro
    1.07
     Pro
    1.07
    PRO
    0.99
     pro
    0.96
    e
    0.95
     trans
    0.93
    O
    0.92
    Act Density 0.119%

    No Known Activations