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

    Neuronpedia

    INDEX
    Explanations

    references to legal documents and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consistent
    -0.98
     consistency
    -0.97
    consistent
    -0.77
     Consistent
    -0.77
     consistently
    -0.77
    consistency
    -0.76
     Consistency
    -0.74
    Consistent
    -0.74
    Consistency
    -0.73
     uniform
    -0.72
    POSITIVE LOGITS
     page
    1.93
     pages
    1.65
    page
    1.62
     p
    1.61
     pp
    1.50
     pg
    1.48
     Page
    1.44
    pages
    1.39
    Page
    1.38
     página
    1.31
    Act Density 1.291%

    No Known Activations