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

    Neuronpedia

    INDEX
    Explanations

    reported speech or quotations from individuals about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.92
     Jefus
    -0.92
     auffi
    -0.84
     purpoſe
    -0.83
     myſelf
    -0.82
     Monfieur
    -0.81
    ſelf
    -0.81
     houſe
    -0.76
     Majefty
    -0.75
     poffible
    -0.75
    POSITIVE LOGITS
     quote
    0.68
     exclaim
    0.62
     remarked
    0.61
     saying
    0.60
     remark
    0.60
     phrase
    0.60
     exclaimed
    0.59
     paraphrase
    0.57
     sarcas
    0.56
     proverb
    0.55
    Act Density 0.347%

    No Known Activations