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

    Neuronpedia

    INDEX
    Explanations

    references to social interactions or engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tena
    -0.43
    .
    -0.42
     oras
    -0.41
     directe
    -0.41
    rsiniz
    -0.41
     вперед
    -0.40
     aprobó
    -0.39
    ھر
    -0.38
     forward
    -0.38
     tropical
    -0.37
    POSITIVE LOGITS
     Roskov
    0.94
     ویکی‌پدی
    0.92
    ########.
    0.83
     kasarigan
    0.80
    ंदीखरीदारी
    0.78
    ]");
    0.75
     bezeichneter
    0.75
    Geplaatst
    0.74
    :+:
    0.73
     بيها
    0.73
    Act Density 0.327%

    No Known Activations