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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating male and female subjects, particularly in relation to their experiences

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

    pronouns as subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.66
    -0.62
     autorytatywna
    -0.61
     Вікіпе
    -0.59
    AddTagHelper
    -0.57
     незавершена
    -0.57
    MigrationBuilder
    -0.57
     noDo
    -0.57
     BoxDecoration
    -0.57
    Referanser
    -0.55
    POSITIVE LOGITS
    ArrowToggle
    0.37
     saw
    0.32
    的
    0.30
    中
    0.29
    évaluateur
    0.29
     की
    0.29
     aner
    0.28
     felt
    0.28
     experiment
    0.27
     zvlá
    0.27
    Act Density 0.045%

    No Known Activations