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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or assurance

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

    be sure to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.53
     utafitiHapana
    -0.49
     arşivlendi
    -0.45
     defaultstate
    -0.45
     ویکی‌پدیا
    -0.45
     Trá
    -0.42
    ixante
    -0.42
     Martinez
    -0.41
    انتهای
    -0.41
     Marín
    -0.41
    POSITIVE LOGITS
     sure
    1.02
     Sure
    0.84
    Sure
    0.83
     SURE
    0.82
    sure
    0.80
     sicuro
    0.65
     gewiß
    0.54
     certitude
    0.51
     säkert
    0.51
     assured
    0.50
    Act Density 0.002%

    No Known Activations