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

    Neuronpedia

    INDEX
    Explanations

    content related to attention and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "attention"

    np_acts-logits-general · gemini-2.0-flash

    attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rabh
    -0.56
    tangentMode
    -0.55
    sy
    -0.55
     McBride
    -0.54
     ExecuteAsync
    -0.54
    erein
    -0.51
    FileDialog
    -0.51
    LayoutPanel
    -0.51
    évaluateur
    -0.50
    დ
    -0.50
    POSITIVE LOGITS
     attention
    1.54
     Attention
    1.46
    Attention
    1.31
    attention
    1.27
     ATTENTION
    1.23
    ATTENTION
    1.19
    attenzione
    1.11
     attentions
    1.09
     aandacht
    1.01
     detail
    0.90
    Act Density 0.071%

    No Known Activations