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

    Neuronpedia

    INDEX
    Explanations

    references to honors and awards within artistic or professional contexts

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

    honor or honored

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.35
    addCriterion
    -0.34
    astéroïdes
    -0.33
     devils
    -0.32
     Tangerang
    -0.32
     demons
    -0.31
    는데
    -0.31
     commercial
    -0.29
     Egipto
    -0.29
     terecht
    -0.29
    POSITIVE LOGITS
     honor
    1.38
    honor
    1.30
     honored
    1.24
     honour
    1.24
     Honor
    1.20
     honoring
    1.18
     honors
    1.17
    Honor
    1.16
     honoured
    1.13
     HONOR
    1.09
    Act Density 0.014%

    No Known Activations