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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns relating to people and family

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

    Possessive pronouns (your, our, their, her, his, its)

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     latine
    -0.57
     nécessairement
    -0.55
    gway
    -0.53
     înc
    -0.52
     disambiguazione
    -0.49
     necessariamente
    -0.47
    ربای
    -0.47
    ishments
    -0.45
    CPtr
    -0.45
     melding
    -0.45
    POSITIVE LOGITS
     equipments
    0.65
    Tembelea
    0.62
     researches
    0.60
    AutoScale
    0.57
     another
    0.56
    bootstrapcdn
    0.55
     sufferings
    0.54
    illiers
    0.54
    ملكة
    0.54
    ]-->
    0.53
    Act Density 0.162%

    No Known Activations