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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive pronouns indicating interaction or involvement with others

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people in the context of relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gee
    -0.63
     dent
    -0.62
    sequence
    -0.61
    ĸļ
    -0.60
    ente
    -0.60
    ctory
    -0.59
    multipl
    -0.58
    ICE
    -0.58
    semb
    -0.58
    Comment
    -0.58
    POSITIVE LOGITS
    selves
    1.02
    atically
    0.80
    atic
    0.78
    self
    0.73
     sorely
    0.70
    overe
    0.69
     loose
    0.68
    ãģ¦
    0.67
    ben
    0.65
    owsky
    0.65
    Act Density 0.151%

    No Known Activations