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

    Neuronpedia

    INDEX
    Explanations

    references to significant environmental phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.08
    3:0.05
    4:0.04
    5:0.05
    6:0.26
    7:0.03
    8:0.05
    9:0.20
    10:0.04
    11:0.02
    Negative Logits
    Thompson
    -3.86
     Williamson
    -3.83
     Wass
    -3.82
    assin
    -3.49
    Lyn
    -3.48
    athe
    -3.48
     Religion
    -3.45
     Lois
    -3.38
     Thom
    -3.36
     Nath
    -3.35
    POSITIVE LOGITS
     bubbles
    9.66
     bubble
    8.93
     Bubble
    8.75
     Bub
    8.03
    bub
    7.90
     balloons
    6.36
     bub
    6.24
     balloon
    5.95
     Balloon
    5.62
     Bounce
    5.61
    Act Density 0.002%

    No Known Activations