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

    Neuronpedia

    INDEX
    Explanations

    references to select groups of people or audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    select few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TextUtils
    -0.33
     måde
    -0.33
    elemField
    -0.31
     bosh
    -0.30
     atracción
    -0.29
     personnalisées
    -0.28
     leçons
    -0.28
    bodyParser
    -0.27
     ternura
    -0.27
     nasional
    -0.27
    POSITIVE LOGITS
     lucky
    1.16
     select
    1.07
     selected
    1.02
    selected
    1.01
     fortunate
    1.00
     brave
    1.00
    lucky
    1.00
     Selected
    0.98
     SELECTED
    0.97
     elite
    0.96
    Act Density 0.100%

    No Known Activations