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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.02
     ſeveral
    -0.95
     Monfieur
    -0.95
     themſelves
    -0.94
     Efq
    -0.91
     himſelf
    -0.91
     raiſ
    -0.90
     itſelf
    -0.89
     Jefus
    -0.86
     whoſe
    -0.84
    POSITIVE LOGITS
     source
    1.61
     Source
    1.52
     sources
    1.50
    Source
    1.45
    source
    1.42
     SOURCE
    1.39
     Sources
    1.35
    SOURCE
    1.33
    Sources
    1.25
    sources
    1.24
    Act Density 0.122%

    No Known Activations