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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.05
    4:0.05
    5:0.03
    6:0.38
    7:0.16
    8:0.03
    9:0.05
    10:0.04
    11:0.07
    Negative Logits
    peat
    -1.42
     compliment
    -1.34
    keyes
    -1.33
    erest
    -1.30
     excuse
    -1.29
    orem
    -1.25
    worms
    -1.25
     seniors
    -1.25
     candles
    -1.23
     cane
    -1.22
    POSITIVE LOGITS
    士
    1.50
    Pain
    1.42
    Catal
    1.41
     opio
    1.40
     Centauri
    1.39
    龍喚士
    1.33
    Wars
    1.21
    usc
    1.20
    los
    1.20
    将
    1.20
    Act Density 0.006%

    No Known Activations