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

    Neuronpedia

    INDEX
    Explanations

    attends to numeric characters from accompanying punctuation marks

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.28
    1:0.32
    2:0.11
    3:0.03
    4:0.04
    5:0.05
    6:0.05
    7:0.08
    Negative Logits
    addPreferredGap
    -0.40
    addGap
    -0.38
    imarães
    -0.33
    YTICAL
    -0.33
    ENCIES
    -0.33
    adalupe
    -0.32
    ]}>
    -0.32
     NSError
    -0.32
    implements
    -0.31
    Brow
    -0.30
    POSITIVE LOGITS
    IntoConstraints
    0.34
     kaarangay
    0.32
    ModelForm
    0.30
     كومونز
    0.30
    AddTagHelper
    0.30
     jambe
    0.30
     ویکی‌پدی
    0.30
     تضيفلها
    0.29
    sizeCache
    0.29
    LError
    0.28
    Act Density 0.023%

    No Known Activations