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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers denoting street names

    oai_token-act-pair · gpt-3.5-turbo

    ordinal indicators, particularly relating to street names or numerical positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.78
    Statistics
    -0.70
    zai
    -0.69
    imilar
    -0.66
    mble
    -0.64
    bath
    -0.62
    itri
    -0.61
    Contract
    -0.58
    etsk
    -0.57
    ãĤĭ
    -0.57
    POSITIVE LOGITS
    ousand
    0.93
     Amendment
    0.89
     Avenue
    0.86
    century
    0.83
     Street
    0.83
     Degree
    0.80
     percentile
    0.79
    degree
    0.79
     Anniversary
    0.78
     Place
    0.77
    Act Density 0.034%

    No Known Activations