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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "paying attention" is used

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of paying attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     halves
    -0.72
    venge
    -0.69
    tre
    -0.68
    lua
    -0.67
    byn
    -0.64
    headers
    -0.64
    ods
    -0.63
     Bees
    -0.63
    joining
    -0.63
    apeshifter
    -0.62
    POSITIVE LOGITS
    é¾įå¥ij士
    0.82
    ibly
    0.76
     absor
    0.71
    IBLE
    0.69
     attent
    0.69
    arios
    0.68
     attentive
    0.65
    ibility
    0.64
    fulness
    0.64
     elsewhere
    0.63
    Act Density 0.019%

    No Known Activations