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

    Neuronpedia

    INDEX
    Explanations

    attends to text formatted in small caps from preceding formatted text

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.14
    2:0.11
    3:0.09
    4:0.11
    5:0.05
    6:0.19
    7:0.15
    Negative Logits
    ниципа
    -0.34
     financially
    -0.32
    RemoveField
    -0.32
    <strong>
    -0.31
     Vand
    -0.31
    amond
    -0.29
    Vand
    -0.28
    het
    -0.28
    [/
    -0.28
    子的
    -0.28
    POSITIVE LOGITS
    NewUrlParser
    0.39
    WebVitals
    0.36
    ExtendWith
    0.35
    AndroidJUnit
    0.32
     useDispatch
    0.31
     mxArray
    0.31
    StoryboardSegue
    0.30
    Décès
    0.30
    iastes
    0.29
     AttributeSet
    0.29
    Act Density 0.048%

    No Known Activations