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

    Neuronpedia

    INDEX
    Explanations

    terms related to paying attention and focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.82
     unknownFields
    -0.69
     Soria
    -0.68
     Audiodateien
    -0.67
     roul
    -0.66
    AntiForgeryToken
    -0.66
    hdashline
    -0.65
    談社
    -0.65
    Revenir
    -0.64
     rencontr
    -0.63
    POSITIVE LOGITS
     attention
    1.43
    attention
    1.17
     Attention
    1.13
     atenção
    1.06
    Attention
    1.05
     attentive
    0.99
     внимание
    0.98
     ATTENTION
    0.92
     focus
    0.88
     atención
    0.87
    Act Density 0.224%

    No Known Activations