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

    Neuronpedia

    INDEX
    Explanations

    words related to historical buildings and architectural structures

    oai_token-act-pair · gpt-3.5-turbo

    references to significant architectural structures and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imester
    -0.77
    ãĥĥãĥī
    -0.68
    Downloadha
    -0.67
    maxwell
    -0.66
     saliva
    -0.64
    ãģĹ
    -0.62
    ACTED
    -0.61
     Competitive
    -0.60
    yon
    -0.60
    efe
    -0.60
    POSITIVE LOGITS
     perched
    0.99
     tower
    0.97
     towers
    0.94
    tower
    0.91
     annex
    0.82
    tyard
    0.81
     plaza
    0.79
     entrance
    0.79
    insula
    0.78
     courtyard
    0.77
    Act Density 0.273%

    No Known Activations