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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.21
     raiſ
    -1.20
     Jefus
    -1.19
     Anſ
    -1.17
     Eſ
    -1.14
     Efq
    -1.14
     Diſ
    -1.13
     Houſe
    -1.12
     Reſ
    -1.11
     faſt
    -1.10
    POSITIVE LOGITS
    ,
    0.89
     (
    0.67
    ↵
    0.65
    ↵↵
    0.62
    .
    0.61
    :
    0.61
    ),
    0.61
      
    0.60
    /
    0.59
    )
    0.59
    Act Density 0.199%

    No Known Activations