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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, especially squares, within a city

    oai_token-act-pair · gpt-3.5-turbo

    references to specific public squares

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urally
    -0.77
    ERAL
    -0.72
    essor
    -0.70
    orship
    -0.70
    é»Ĵ
    -0.69
    hetical
    -0.69
    eworld
    -0.68
    opathy
    -0.66
    ogical
    -0.66
    ãģ®éŃĶ
    -0.65
    POSITIVE LOGITS
     Enix
    1.41
     Mile
    0.90
    pants
    0.85
    Square
    0.78
     Square
    0.77
     Feet
    0.71
    cars
    0.71
    asaki
    0.69
    ¾
    0.69
    faces
    0.69
    Act Density 0.012%

    No Known Activations