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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens marked with double underscores from tokens marked with double brackets

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.54
    2:0.07
    3:0.04
    4:0.05
    5:0.06
    6:0.03
    7:0.07
    Negative Logits
     Cassini
    -0.54
     للمعارف
    -0.49
    原始内容存档于
    -0.47
    )|^{
    -0.47
     uska
    -0.45
     الحره
    -0.45
    <![
    -0.45
    PyExc
    -0.45
    ::<
    -0.45
    "]/
    -0.43
    POSITIVE LOGITS
    homonymie
    0.35
     is
    0.35
    ty
    0.32
     yyj
    0.31
     éduc
    0.31
    хьтан
    0.30
    onViewCreated
    0.30
     île
    0.29
    TimerTask
    0.29
    SharedDtor
    0.29
    Act Density 0.463%

    No Known Activations