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

    Neuronpedia

    INDEX
    Explanations

    markers denoting citation contexts or references within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.06
    2:0.14
    3:0.08
    4:0.06
    5:0.11
    6:0.03
    7:0.02
    8:0.04
    9:0.10
    10:0.08
    11:0.03
    Negative Logits
    zi
    -1.88
    ó
    -1.76
    opian
    -1.75
    sudo
    -1.72
    ilar
    -1.69
    azes
    -1.69
    ](
    -1.69
    iasis
    -1.69
    ozy
    -1.68
    rat
    -1.65
    POSITIVE LOGITS
     Strateg
    1.78
     Maurit
    1.69
     Wilmington
    1.65
     Azerb
    1.62
     Richmond
    1.60
     Blooming
    1.59
     Priv
    1.58
     Aerial
    1.57
     Kell
    1.57
     Located
    1.55
    Act Density 0.000%

    No Known Activations