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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to drawing attention and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    887
    -0.15
    orman
    -0.14
    hist
    -0.14
    еÑī
    -0.14
    æ¨
    -0.13
    ела
    -0.13
    avicon
    -0.13
    æĬ±
    -0.13
    venir
    -0.13
    apo
    -0.13
    POSITIVE LOGITS
     attention
    0.97
    attention
    0.81
     Attention
    0.78
    Attention
    0.70
     attent
    0.60
     atención
    0.59
    _attention
    0.59
     внимание
    0.59
    注æĦı
    0.54
     attn
    0.50
    Act Density 0.133%

    No Known Activations