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

    Neuronpedia

    INDEX
    Explanations

    references to issues of attention and distraction in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iren
    -0.15
    èĥĨ
    -0.14
    ·
    -0.14
    oji
    -0.13
     UV
    -0.13
    irim
    -0.13
    æij¸
    -0.13
    yth
    -0.13
    TECTED
    -0.13
    uhe
    -0.13
    POSITIVE LOGITS
     attention
    0.59
     Attention
    0.54
    attention
    0.49
    Attention
    0.49
     attent
    0.41
     paying
    0.39
     attentive
    0.37
    _attention
    0.36
     pay
    0.35
     focus
    0.35
    Act Density 0.035%

    No Known Activations