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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "house" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergies
    -0.94
     reaſon
    -0.88
     Raptors
    -0.85
     geox
    -0.84
     ſmall
    -0.83
     Avid
    -0.83
    atonin
    -0.82
     twine
    -0.82
     fidélité
    -0.82
     sequins
    -0.82
    POSITIVE LOGITS
     house
    2.22
     House
    2.10
    House
    1.95
     houses
    1.91
    house
    1.89
     HOUSE
    1.76
     Houses
    1.69
    HOUSE
    1.68
    houses
    1.62
    Houses
    1.60
    Act Density 0.048%

    No Known Activations