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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Peter."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.92
     itſelf
    -0.85
     myſelf
    -0.84
     raiſ
    -0.83
    =$?
    -0.82
     himſelf
    -0.78
     poffible
    -0.77
     pleaſure
    -0.77
     themſelves
    -0.77
     Fais
    -0.75
    POSITIVE LOGITS
     Peter
    1.49
    Peter
    1.40
     PETER
    1.25
    PETER
    1.23
    peter
    1.14
     Peters
    1.09
     peter
    1.05
    Peters
    1.04
     Peterborough
    1.01
     Pete
    0.91
    Act Density 0.004%

    No Known Activations