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

    Neuronpedia

    INDEX
    Explanations

    references to historical timelines and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.03
    3:0.15
    4:0.12
    5:0.09
    6:0.12
    7:0.04
    8:0.14
    9:0.07
    10:0.01
    11:0.03
    Negative Logits
     Omaha
    -1.45
     wartime
    -1.43
    ppa
    -1.43
     ­
    -1.40
    elight
    -1.39
     nationally
    -1.37
     victory
    -1.37
    Thumbnail
    -1.35
     workplaces
    -1.35
     overnight
    -1.35
    POSITIVE LOGITS
    Reviewer
    1.97
    Downloadha
    1.96
    evidence
    1.77
    DragonMagazine
    1.73
    ibaba
    1.70
    yrics
    1.64
    etheless
    1.62
     avg
    1.61
    ?)
    1.60
    ?),
    1.59
    Act Density 0.350%

    No Known Activations