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

    Neuronpedia

    INDEX
    Explanations

    references to attention and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFIED
    -0.16
    ped
    -0.15
    æ§
    -0.15
    kits
    -0.15
    ovich
    -0.15
    inho
    -0.14
    ediator
    -0.14
    ISOString
    -0.14
    yard
    -0.14
    jour
    -0.14
    POSITIVE LOGITS
     Attention
    0.24
     attention
    0.24
     paid
    0.23
    al
    0.20
    Attention
    0.19
    åĬĽ
    0.19
    attention
    0.19
    ENTION
    0.18
     Paid
    0.17
    Paid
    0.17
    Act Density 0.019%

    No Known Activations