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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to legal or organizational terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     getElement
    -0.70
    arcas
    -0.69
    ХОД
    -0.62
     Howe
    -0.62
     estimés
    -0.62
     Fortaleza
    -0.62
     Rhodes
    -0.61
     lég
    -0.60
     Kapp
    -0.60
     Lazar
    -0.60
    POSITIVE LOGITS
     Garr
    0.97
    !("{
    0.94
    AndEndTag
    0.92
     Toni
    0.84
     Saline
    0.83
     SAL
    0.79
    Obrázky
    0.79
    Bissau
    0.76
    ροι
    0.76
    SAL
    0.76
    Act Density 3.191%

    No Known Activations