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

    Neuronpedia

    INDEX
    Explanations

    references to geographical features, such as hills, mountains, and villages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    漏
    -0.54
    挑
    -0.51
    棒
    -0.49
    grafico
    -0.47
    igare
    -0.47
    DataAnnotations
    -0.47
    宙
    -0.47
    退
    -0.46
    存
    -0.46
     مغ
    -0.46
    POSITIVE LOGITS
     hills
    1.72
     villages
    1.72
     countryside
    1.70
     village
    1.69
     hillside
    1.51
     valley
    1.50
     mountains
    1.50
     suburbs
    1.48
     town
    1.46
     hilly
    1.45
    Act Density 2.300%

    No Known Activations