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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns, particularly "you" and "me."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.92
     Rasul
    -0.89
    TypedDataSet
    -0.88
    UnusedPrivate
    -0.88
     gynnwys
    -0.82
     decon
    -0.81
    ///</
    -0.81
     Jefus
    -0.78
     deſt
    -0.77
    TagMode
    -0.77
    POSITIVE LOGITS
     in
    0.79
     him
    0.77
     with
    0.72
     from
    0.71
    เอง
    0.70
     on
    0.69
     as
    0.69
     them
    0.69
     her
    0.67
     to
    0.65
    Act Density 0.245%

    No Known Activations