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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.06
    3:0.03
    4:0.05
    5:0.02
    6:0.24
    7:0.06
    8:0.05
    9:0.30
    10:0.03
    11:0.03
    Negative Logits
    wcs
    -3.86
     Saga
    -3.56
     Cambodia
    -3.54
     Bosnia
    -3.48
     dried
    -3.48
     Meadow
    -3.46
     ABE
    -3.44
     condom
    -3.44
    orkshire
    -3.43
    avage
    -3.43
    POSITIVE LOGITS
    Leon
    10.55
     Leon
    8.72
     Leonard
    8.41
    leon
    7.38
     Leonardo
    5.08
    STAR
    4.61
     Anton
    4.39
     Leo
    4.09
     Levine
    4.07
     Levy
    3.87
    Act Density 0.003%

    No Known Activations