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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns or references to ownership

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

    possessive pronoun followed by attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BufferException
    -0.43
    inaison
    -0.43
     jegy
    -0.40
    atmosphère
    -0.39
    échelle
    -0.39
    affaire
    -0.38
     ocio
    -0.37
    NSNotification
    -0.37
     köny
    -0.37
    SpringBootTest
    -0.37
    POSITIVE LOGITS
     being
    0.55
    TypedDataSet
    0.54
     sự
    0.54
     ability
    0.49
     Fähigkeit
    0.48
     commitment
    0.48
     inability
    0.46
    GIH
    0.46
    complexContent
    0.46
     להיות
    0.46
    Act Density 0.115%

    No Known Activations