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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns or direct address in conversation

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

    vous followed by pourrait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.65
    ContentAsync
    -0.60
     feroit
    -0.54
    oa̍t
    -0.52
    httphttps
    -0.52
     nôtre
    -0.52
     auroit
    -0.50
    apnews
    -0.49
    LookAnd
    -0.48
     proprement
    -0.48
    POSITIVE LOGITS
     vous
    1.23
     Vous
    0.98
    Vous
    0.92
    vous
    0.90
    Vos
    0.87
     VOUS
    0.83
     vos
    0.78
     Vos
    0.75
    Вам
    0.71
    you
    0.69
    Act Density 0.001%

    No Known Activations