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

    Neuronpedia

    INDEX
    Explanations

    numerical values and significant data points related to statistics and politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.19
    1:0.07
    2:0.06
    3:0.05
    4:0.05
    5:0.10
    6:0.02
    7:0.03
    8:0.28
    9:0.04
    10:0.03
    11:0.04
    Negative Logits
    �
    -1.88
     "$:/
    -1.64
     GDDR
    -1.58
    Merit
    -1.55
    �
    -1.53
    ャ
    -1.47
     Viet
    -1.45
    ETF
    -1.42
    TF
    -1.41
    aucuses
    -1.41
    POSITIVE LOGITS
    _.
    1.98
    +.
    1.96
    .","
    1.77
    "},"
    1.75
    .#
    1.71
    .(
    1.70
     dunno
    1.64
     stroke
    1.63
     Tsukuyomi
    1.62
    ;}
    1.59
    Act Density 0.006%

    No Known Activations