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

    Neuronpedia

    INDEX
    Explanations

    actions and phrases related to attention and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hist
    -0.15
    alez
    -0.15
    avicon
    -0.14
    overe
    -0.14
    ела
    -0.14
    æĬ±
    -0.13
    ÑĩаÑĤ
    -0.13
    еÑī
    -0.13
    abra
    -0.13
    ANNEL
    -0.13
    POSITIVE LOGITS
     attention
    0.95
    attention
    0.80
     Attention
    0.78
    Attention
    0.69
     atención
    0.60
     внимание
    0.60
     attent
    0.59
    _attention
    0.59
     ATT
    0.52
    注æĦı
    0.52
    Act Density 0.171%

    No Known Activations