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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals, particularly focusing on gendered and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.82
    पया
    -0.69
    bootstrapcdn
    -0.65
     snippetHide
    -0.64
    AnchorStyles
    -0.64
     فريبيس
    -0.64
    ContentAsync
    -0.62
     TextInputType
    -0.62
    DBNull
    -0.62
    LookAndFeel
    -0.60
    POSITIVE LOGITS
     Her
    0.75
    Her
    0.72
    rungsseite
    0.70
    contentLoaded
    0.64
     kasarigan
    0.61
    she
    0.61
     &___
    0.59
     SEDS
    0.57
     CURIAM
    0.56
     HER
    0.55
    Act Density 0.216%

    No Known Activations