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

    Neuronpedia

    INDEX
    Explanations

    references to sitting or seating positions and related actions

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

    sitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trekken
    -0.45
     coverage
    -0.44
     physical
    -0.43
     SafeMath
    -0.43
     phase
    -0.41
     Physical
    -0.41
     opération
    -0.41
     ferons
    -0.40
     operasi
    -0.39
     confiança
    -0.39
    POSITIVE LOGITS
     Seat
    0.85
     seat
    0.81
     Seating
    0.80
     seating
    0.79
    Seat
    0.77
    坐
    0.77
     chair
    0.76
     chairs
    0.74
     sitting
    0.74
     sentarse
    0.73
    Act Density 0.024%

    No Known Activations