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

    Neuronpedia

    INDEX
    Explanations

    concepts related to dominance and influence within various institutions and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.06
    4:0.02
    5:0.04
    6:0.10
    7:0.12
    8:0.04
    9:0.05
    10:0.07
    11:0.34
    Negative Logits
    orrow
    -1.54
    ividual
    -1.33
    psey
    -1.33
    obyl
    -1.28
    etooth
    -1.25
    ectar
    -1.20
    etimes
    -1.20
    elaide
    -1.19
    azeera
    -1.19
    etheus
    -1.18
    POSITIVE LOGITS
     (>
    1.78
     imaginable
    1.48
     EVER
    1.41
     (<
    1.24
     nowadays
    1.22
     dominates
    1.15
    -+-+
    1.09
     viz
    1.07
    ever
    1.07
     (−
    1.07
    Act Density 0.009%

    No Known Activations