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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or description of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.01
     ſtate
    -0.98
     dafs
    -0.98
     myſelf
    -0.98
     Chriftian
    -0.94
     houſe
    -0.94
     ſever
    -0.90
     itſelf
    -0.89
     themſelves
    -0.89
     purpoſe
    -0.88
    POSITIVE LOGITS
     è
    1.11
     is
    1.02
     ist
    1.00
     a
    0.95
     be
    0.94
     suis
    0.91
     là
    0.90
     είναι
    0.86
     est
    0.85
    ίναι
    0.84
    Act Density 0.019%

    No Known Activations