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

    Neuronpedia

    INDEX
    Explanations

    references to a "house" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergies
    -0.97
     bershka
    -0.94
     ſmall
    -0.93
     myſelf
    -0.93
     ſever
    -0.93
     geox
    -0.93
     ſeveral
    -0.93
    Calais
    -0.92
     ſhall
    -0.91
     reaſon
    -0.91
    POSITIVE LOGITS
     house
    2.63
     House
    2.46
    House
    2.29
     houses
    2.27
    house
    2.16
     HOUSE
    2.14
     Houses
    2.02
    HOUSE
    2.00
    Houses
    1.88
    houses
    1.88
    Act Density 0.043%

    No Known Activations