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

    Neuronpedia

    INDEX
    Explanations

    references to rankings or lists of top players or teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.15
    2:0.04
    3:0.03
    4:0.03
    5:0.21
    6:0.05
    7:0.02
    8:0.07
    9:0.04
    10:0.09
    11:0.04
    Negative Logits
    bec
    -2.11
    gur
    -2.04
    sim
    -1.83
    mobi
    -1.83
    imil
    -1.80
    abiding
    -1.77
    akin
    -1.76
    nu
    -1.76
    conn
    -1.75
    handler
    -1.74
    POSITIVE LOGITS
     Ranking
    2.07
     52
    2.04
     list
    1.94
     Quarter
    1.77
     twenties
    1.74
     50
    1.74
     rankings
    1.74
     quarter
    1.73
    UFC
    1.72
     ranking
    1.71
    Act Density 0.003%

    No Known Activations