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

    Neuronpedia

    INDEX
    Explanations

    text structure indicators or delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.89
    WebServlet
    -0.75
    Билгалдахарш
    -0.74
    Tembelea
    -0.70
    Fordítás
    -0.67
    extAlignment
    -0.66
     <>",
    -0.66
    Amicalement
    -0.66
    AllAfrica
    -0.65
    shields
    -0.65
    POSITIVE LOGITS
     homeowners
    0.86
     Residential
    0.75
     residential
    0.74
     installation
    0.73
     homeowner
    0.72
     household
    0.71
     residencial
    0.69
     Home
    0.65
     install
    0.64
     home
    0.63
    Act Density 0.221%

    No Known Activations