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

    Neuronpedia

    INDEX
    Explanations

    locations or geographic areas

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographic area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lett
    -0.81
    rating
    -0.77
    enstein
    -0.72
    gement
    -0.72
    Glass
    -0.69
    fruit
    -0.68
    thood
    -0.68
    icer
    -0.68
    fig
    -0.66
    士
    -0.64
    POSITIVE LOGITS
     vicinity
    1.02
     periphery
    0.88
     surrounding
    0.88
     area
    0.87
     countryside
    0.79
     adjacent
    0.77
     Territories
    0.75
     bounded
    0.75
     frequ
    0.75
     illegally
    0.72
    Act Density 0.067%

    No Known Activations