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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.69
    ĸļ
    -0.65
    heny
    -0.64
     largeDownload
    -0.64
    NetMessage
    -0.61
    gor
    -0.60
     Sund
    -0.58
     Fulton
    -0.58
     Radar
    -0.57
     "{
    -0.56
    POSITIVE LOGITS
    selves
    1.06
    self
    0.99
    atic
    0.85
    soever
    0.79
     accordingly
    0.76
    lees
    0.76
     mentally
    0.75
    alian
    0.75
     personally
    0.74
     emotionally
    0.74
    Act Density 0.193%

    No Known Activations