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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain conversational markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.70
     ſtate
    -0.66
     Monfieur
    -0.61
     Fonction
    -0.60
     ſta
    -0.60
     Houſe
    -0.59
     iſt
    -0.59
     purpoſe
    -0.59
    ükemmel
    -0.58
     Perſ
    -0.58
    POSITIVE LOGITS
    ThroughAttribute
    0.75
     ExecuteAsync
    0.72
     Vikipedi
    0.68
     cherchés
    0.67
    AndEndTag
    0.65
    RenderAtEndOf
    0.64
    SequentialGroup
    0.63
     AssemblyCulture
    0.60
    @[+][
    0.60
    出版年
    0.59
    Act Density 0.082%

    No Known Activations