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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and expressions of ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     along
    -0.81
    uve
    -0.70
    ciation
    -0.70
    ibaba
    -0.66
    uate
    -0.66
    ocument
    -0.66
    river
    -0.66
    vine
    -0.66
     Farrell
    -0.64
     Airl
    -0.64
    POSITIVE LOGITS
     own
    1.48
    self
    1.38
    selves
    1.30
     surroundings
    1.21
    elf
    1.05
     peers
    1.04
     destiny
    0.98
    ELF
    0.97
     OWN
    0.97
     predecessors
    0.90
    Act Density 0.278%

    No Known Activations