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

    Neuronpedia

    INDEX
    Explanations

    mentions of "house" and its variations, indicating a focus on real estate or domestic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergies
    -1.07
     Raptors
    -0.89
     Wilfred
    -0.86
     Avid
    -0.86
    betic
    -0.85
     punctures
    -0.84
     Mercan
    -0.83
     reaſon
    -0.82
     Czy
    -0.82
     bershka
    -0.82
    POSITIVE LOGITS
     house
    1.55
     House
    1.47
     houses
    1.46
    House
    1.37
    house
    1.33
     Houses
    1.27
    Houses
    1.25
     HOUSE
    1.21
    houses
    1.20
     Hous
    1.18
    Act Density 0.082%

    No Known Activations