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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and possessions

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

    Personal pronouns followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive determiners and subsequent nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.76
    Ծանոթ
    -0.66
     decidedly
    -0.66
    ishments
    -0.65
    MemoryWarning
    -0.65
     disambiguazione
    -0.65
    ReusableCell
    -0.65
    הערות
    -0.65
    ponym
    -0.63
    transQ
    -0.59
    POSITIVE LOGITS
     equipments
    0.66
     advices
    0.64
     another
    0.63
    AutoScale
    0.63
     evidences
    0.61
     stuffs
    0.57
     functionalities
    0.56
     each
    0.53
     feedbacks
    0.51
     dialogues
    0.51
    Act Density 0.172%

    No Known Activations