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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns referring to personal ownership or connection

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

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.52
    InstrumentedTest
    -0.50
    KindOfClass
    -0.49
    expandindo
    -0.47
    glBind
    -0.47
     juſ
    -0.47
    vább
    -0.46
     Tatsache
    -0.46
    taient
    -0.46
    HttpEntity
    -0.44
    POSITIVE LOGITS
     own
    1.02
     their
    1.02
     his
    0.95
    Their
    0.88
     your
    0.86
     ihrer
    0.84
     my
    0.84
    their
    0.82
     Their
    0.82
     His
    0.81
    Act Density 0.455%

    No Known Activations