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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by words indicating a personal connection or emotion

    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
    vine
    -0.90
     along
    -0.78
     thereof
    -0.67
     headquartered
    -0.65
    cour
    -0.64
    izu
    -0.63
     Barron
    -0.63
    edia
    -0.63
    ï¸
    -0.63
    river
    -0.63
    POSITIVE LOGITS
     own
    1.65
    self
    1.38
    selves
    1.20
     surroundings
    1.16
     OWN
    1.10
     newfound
    1.08
     peers
    1.05
     destiny
    0.99
    ELF
    0.93
     predecessors
    0.90
    Act Density 0.350%

    No Known Activations