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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and discussions about the blood-brain barrier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.04
    2:0.09
    3:0.05
    4:0.07
    5:0.04
    6:0.18
    7:0.05
    8:0.12
    9:0.12
    10:0.04
    11:0.04
    Negative Logits
     Lev
    -4.55
     Guth
    -4.14
     Slay
    -3.68
     Gn
    -3.66
     Lyon
    -3.59
     Salam
    -3.53
     Cunningham
    -3.49
     Lun
    -3.48
     Gingrich
    -3.46
     Flynn
    -3.45
    POSITIVE LOGITS
     BB
    9.05
    BB
    7.61
    bb
    4.08
     Bee
    3.94
     KB
    3.87
     Bubble
    3.70
    PB
    3.66
     AAA
    3.66
    AAA
    3.65
     Jar
    3.52
    Act Density 0.001%

    No Known Activations