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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptors of prominence or superiority, such as "largest," "best," and "most."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.67
     transférez
    -0.66
     فريبيس
    -0.62
     vulgaires
    -0.57
     Colleagues
    -0.57
     effray
    -0.56
     становника
    -0.56
     дописавши
    -0.55
    WriteLiteral
    -0.55
     تانيه
    -0.55
    POSITIVE LOGITS
     single
    0.69
    iest
    0.61
    urably
    0.60
     non
    0.60
     thing
    0.58
    asson
    0.57
     pure
    0.57
    holi
    0.56
    niest
    0.54
     private
    0.54
    Act Density 0.203%

    No Known Activations