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

    Neuronpedia

    INDEX
    Explanations

    mentions of indoor spaces

    oai_token-act-pair · gpt-3.5-turbo

    mentions of indoor environments or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.83
    erker
    -0.80
    dinand
    -0.76
    awed
    -0.76
    urai
    -0.74
    bsite
    -0.73
    erk
    -0.73
    azaki
    -0.72
    awaru
    -0.72
    uyomi
    -0.71
    POSITIVE LOGITS
     indoor
    0.85
     indoors
    0.80
    spection
    0.78
     Garden
    0.76
     plumbing
    0.76
     gardening
    0.71
     Temperature
    0.69
     outdoor
    0.69
    vention
    0.69
     Monitor
    0.68
    Act Density 0.011%

    No Known Activations