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

    Neuronpedia

    INDEX
    Explanations

    references to sections, notes, and subsections within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blue
    -0.56
    ...
    -0.54
    homonymie
    -0.54
     multiple
    -0.53
    imia
    -0.52
    idere
    -0.51
     mar
    -0.50
     he
    -0.49
     nước
    -0.49
     t
    -0.48
    POSITIVE LOGITS
     $_"
    0.85
     myſelf
    0.84
     Theſe
    0.80
     Monfieur
    0.80
     صوتيه
    0.80
     ainfi
    0.79
     Efq
    0.79
    الحياه
    0.78
     auffi
    0.76
    ✨:
    0.76
    Act Density 1.103%

    No Known Activations