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

    Neuronpedia

    INDEX
    Explanations

    pronouns or possessive determiners indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arios
    -0.92
    adobe
    -0.87
    olkien
    -0.85
    ocument
    -0.83
    lahoma
    -0.79
    zzo
    -0.79
    angular
    -0.78
    sterdam
    -0.77
    aneers
    -0.77
    ACP
    -0.76
    POSITIVE LOGITS
     Majesty
    1.21
     majesty
    1.13
     deepest
    0.91
     downfall
    0.87
     own
    0.87
     finest
    0.85
     sensibilities
    0.85
     favorite
    0.85
     footsteps
    0.85
     displeasure
    0.83
    Act Density 0.296%

    No Known Activations