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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the word "ja"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Ja."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.90
    sworth
    -0.87
    grounds
    -0.75
    mate
    -0.74
    sheet
    -0.74
    holders
    -0.71
    ship
    -0.70
    Catal
    -0.70
    lip
    -0.70
    loo
    -0.68
    POSITIVE LOGITS
    quez
    1.13
    ques
    0.94
    udeau
    0.90
    Å¡
    0.88
    ja
    0.88
    ð
    0.87
    Äĩ
    0.87
    ñ
    0.87
    zyk
    0.85
    vel
    0.84
    Act Density 0.013%

    No Known Activations