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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and political controversies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     zoning
    -0.90
     miscarriage
    -0.87
     shroud
    -0.81
     hemor
    -0.81
     dust
    -0.81
     Borough
    -0.79
     plat
    -0.78
     Mayo
    -0.78
     Augusta
    -0.78
     grips
    -0.76
    POSITIVE LOGITS
    ¹
    1.32
    ª
    1.21
    ł
    1.12
    ı
    1.11
    »
    1.11
    £
    1.08
    ¸
    1.08
    ¾
    1.07
    ¼
    1.06
    ²
    1.05
    Act Density 7.703%

    No Known Activations