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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrasting or comparative relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.81
     houſe
    -0.73
     ſaid
    -0.71
     Theſe
    -0.69
     Majefty
    -0.68
     Inscrivez
    -0.64
     chofe
    -0.64
     Saltar
    -0.63
     ſtand
    -0.63
     pleaſure
    -0.62
    POSITIVE LOGITS
    parsedMessage
    0.95
    ViewFeatures
    0.92
    Diweddarwch
    0.87
     estekak
    0.86
    bewerken
    0.85
    かわらず
    0.82
     Walkover
    0.81
    oa̍t
    0.81
    Datuak
    0.80
    yntaxException
    0.79
    Act Density 0.404%

    No Known Activations