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

    Neuronpedia

    INDEX
    Explanations

    words related to gaining or attracting attention and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaki
    -0.15
    Å¡ek
    -0.15
    SSERT
    -0.14
    oppable
    -0.14
    -coordinate
    -0.14
    HandlerContext
    -0.14
    astos
    -0.14
     Richardson
    -0.14
    uilder
    -0.14
    iom
    -0.14
    POSITIVE LOGITS
     attention
    0.39
    attention
    0.32
    Attention
    0.28
     Attention
    0.27
     headlines
    0.26
     notice
    0.25
     interest
    0.24
    _attention
    0.22
     atención
    0.22
     buzz
    0.21
    Act Density 0.091%

    No Known Activations