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

    Neuronpedia

    INDEX
    Explanations

    references to comfortable seating arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following prepositions related to sitting

    np_acts-logits-general · gemini-2.0-flash

    chairs and seating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    habad
    -0.49
    ovács
    -0.47
     }{@
    -0.46
     réfé
    -0.46
     تانيه
    -0.46
    mills
    -0.45
    ticale
    -0.43
    lloworld
    -0.43
    mella
    -0.42
     Tong
    -0.41
    POSITIVE LOGITS
     seat
    2.30
     chair
    2.22
     seats
    2.21
     chairs
    2.19
     seating
    2.18
     sitting
    2.03
     sit
    1.98
     seated
    1.94
     Seat
    1.93
     Seating
    1.90
    Act Density 0.215%

    No Known Activations