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

    Neuronpedia

    INDEX
    Explanations

    mentions of objects related to bedding or resting places

    oai_token-act-pair · gpt-3.5-turbo

    references to beds and bedding-related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.97
    İĭ
    -0.83
    auga
    -0.79
    vernment
    -0.71
    phies
    -0.70
    rencies
    -0.70
    ãĥ£
    -0.66
    iferation
    -0.64
    Ľ
    -0.63
    opol
    -0.62
    POSITIVE LOGITS
    ding
    1.28
    ded
    1.07
    room
    1.02
    ridden
    1.02
    stead
    1.00
    spread
    0.96
    side
    0.96
    sheet
    0.94
    lam
    0.94
    rock
    0.93
    Act Density 0.019%

    No Known Activations