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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -1.03
    ///</
    -1.00
    TagMode
    -0.93
     Roskov
    -0.91
    rungsseite
    -0.91
    TypedDataSet
    -0.88
     '\\;'
    -0.81
    IndentedString
    -0.81
    <bos>
    -0.81
    httphttps
    -0.81
    POSITIVE LOGITS
     him
    0.81
     us
    0.69
     me
    0.65
     honom
    0.64
     Him
    0.61
     on
    0.61
     them
    0.61
     in
    0.60
     her
    0.59
     as
    0.56
    Act Density 0.221%

    No Known Activations