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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns and possessive determiners, particularly for "his" and "her"

    oai_token-act-pair · gpt-3.5-turbo

    references to a person's characteristics or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -1.08
    igate
    -0.86
    uve
    -0.84
    ocument
    -0.82
    arios
    -0.82
    γ
    -0.81
    osate
    -0.80
    ppo
    -0.80
    onda
    -0.79
    lahoma
    -0.79
    POSITIVE LOGITS
     detractors
    1.27
     contemporaries
    1.26
     demeanor
    1.25
     personality
    1.18
     accomplishments
    1.17
     temperament
    1.14
     penchant
    1.12
     psyche
    1.10
     own
    1.07
     upbringing
    1.07
    Act Density 0.359%

    No Known Activations