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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the start of a new section or block of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.84
     ModelExpression
    -0.82
    AddHtmlAttribute
    -0.78
     Orrell
    -0.74
    Билгалдахарш
    -0.74
    ist
    -0.72
     Ceramby
    -0.70
    WithIOException
    -0.68
    ẵn
    -0.66
     Ades
    -0.66
    POSITIVE LOGITS
     Vous
    1.13
     Вы
    0.96
     vostri
    0.95
     вы
    0.91
    Vous
    0.91
     vous
    0.85
     yourselves
    0.85
    Вы
    0.85
     您
    0.85
    Ваш
    0.84
    Act Density 0.025%

    No Known Activations