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

    Neuronpedia

    INDEX
    Explanations

    references to personal possessions and identity

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

    Possessive pronouns followed by nouns/ideas

    np_acts-logits-general · gemini-2.0-flash

    my fancy, renaissance, eye, mind, shoulders, training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daerah
    -0.45
    žnost
    -0.42
     consig
    -0.41
     onCancelled
    -0.40
    onAttach
    -0.40
    언
    -0.40
    Дан
    -0.38
     ویکی‌پدیای
    -0.38
    jsdelivr
    -0.38
     Daerah
    -0.38
    POSITIVE LOGITS
    verwijspagina
    0.93
     متعلقه
    0.73
     nahilalakip
    0.72
     attention
    0.72
    SharedCtor
    0.72
     Савезне
    0.70
     disambiguazione
    0.69
     senses
    0.69
     ujednoznacz
    0.69
     imagination
    0.68
    Act Density 0.164%

    No Known Activations