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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and auxiliary verbs

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

    past tense verbs and auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.53
    parsedMessage
    -0.52
     houſe
    -0.52
     ſche
    -0.50
    ſelf
    -0.49
     saveiro
    -0.49
     ſch
    -0.48
     pleaſure
    -0.47
    Портали
    -0.46
     faſt
    -0.45
    POSITIVE LOGITS
     wurde
    1.48
     wurden
    1.30
    wurde
    1.09
     został
    0.89
     zostało
    0.87
     została
    0.81
     werd
    0.75
     zosta
    0.74
     zostały
    0.73
     blev
    0.72
    Act Density 0.001%

    No Known Activations