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

    Neuronpedia

    INDEX
    Explanations

    attends to function-related tokens from script-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.11
    2:0.11
    3:0.13
    4:0.11
    5:0.09
    6:0.19
    7:0.13
    Negative Logits
    expandindo
    -0.34
    entary
    -0.27
    ")->
    -0.27
    DebuggerStep
    -0.27
    ().__
    -0.26
    fromnode
    -0.26
    didSet
    -0.26
    ‚¬
    -0.26
     AttributeSet
    -0.25
    errHandler
    -0.25
    POSITIVE LOGITS
    Vidite
    0.32
     فريبيس
    0.26
    HasAnnotation
    0.26
    enumii
    0.25
    әрмәләр
    0.25
    featureID
    0.25
    ViewImports
    0.25
    forRoot
    0.25
     సౌకర్య
    0.24
     éner
    0.24
    Act Density 0.087%

    No Known Activations