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

    Neuronpedia

    INDEX
    Explanations

    past tense variations of the word "work."

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

    worked with or successfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rarity
    -0.44
     tramonto
    -0.43
     dusk
    -0.43
    PointSize
    -0.42
     desconoc
    -0.41
     mocy
    -0.41
    anskje
    -0.40
     Umbrella
    -0.40
    stunde
    -0.40
    gridy
    -0.40
    POSITIVE LOGITS
     worked
    1.74
     Worked
    1.70
    worked
    1.66
    Worked
    1.61
     trabajó
    1.05
     lavorato
    0.95
     travaillé
    0.95
     trabajado
    0.94
    working
    0.90
     working
    0.90
    Act Density 0.004%

    No Known Activations