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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or assurance

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

    expresses certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ciaż
    -0.61
     McFadden
    -0.48
    amaño
    -0.48
    mpo
    -0.47
     Bateman
    -0.47
     McManus
    -0.46
     whilst
    -0.46
    çı
    -0.45
     an
    -0.44
    Whilst
    -0.43
    POSITIVE LOGITS
     sure
    1.77
    sure
    1.54
    Sure
    1.47
     Sure
    1.45
     SURE
    1.38
     sûr
    0.97
     sicuro
    0.88
     certeza
    0.83
     sûre
    0.82
     sicura
    0.79
    Act Density 0.008%

    No Known Activations