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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and related terms indicating ownership or belonging

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

    possessive pronouns before nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogno
    -0.40
     sogni
    -0.38
     dreamed
    -0.35
     amantes
    -0.34
     sueños
    -0.34
     sabores
    -0.34
    InjectMocks
    -0.34
     flavors
    -0.34
     músicas
    -0.34
     créativité
    -0.34
    POSITIVE LOGITS
     informée
    0.68
     ſind
    0.62
     myſelf
    0.55
     chofe
    0.54
    chism
    0.50
    hObject
    0.49
    ſelf
    0.49
     clim
    0.48
    mender
    0.48
     itſelf
    0.48
    Act Density 0.146%

    No Known Activations