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

    Neuronpedia

    INDEX
    Explanations

    references to benefits or advantages in various contexts

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

    benefit or privilege

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Christensen
    -0.43
    Архівовано
    -0.42
     Knudsen
    -0.39
    สือ
    -0.35
    mfenced
    -0.35
     seabed
    -0.35
     
    -0.35
     geleden
    -0.35
     volledige
    -0.35
    стви
    -0.34
    POSITIVE LOGITS
     perks
    1.94
     perk
    1.91
     Perks
    1.61
    perk
    1.50
    quisites
    0.83
    bonus
    0.80
     bonus
    0.80
     vantagem
    0.79
     ventajas
    0.77
    特典
    0.77
    Act Density 0.003%

    No Known Activations